Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5095 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 14.2884. Min Range: -14.2884
Max Act: 14.2884. Min Act: -0.1700
Data Index: 573578 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.2884. Min Range: -14.2884
Max Act: 13.8509. Min Act: -0.1700
Data Index: 7039225 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.2884. Min Range: -14.2884
Max Act: 13.8509. Min Act: -0.1700
Data Index: 8766391 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.2884. Min Range: -14.2884
Max Act: 13.7259. Min Act: -0.1700
Data Index: 8360279 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.2884. Min Range: -14.2884
Max Act: 13.6009. Min Act: -0.1700
Data Index: 1093860 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.2884. Min Range: -14.2884
Max Act: 13.5384. Min Act: -0.1700
Data Index: 6935427 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.2884. Min Range: -14.2884
Max Act: 13.5384. Min Act: -0.1700
Data Index: 8618718 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.2884. Min Range: -14.2884
Max Act: 13.3509. Min Act: -0.1700
Data Index: 527953 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.2884. Min Range: -14.2884
Max Act: 13.3509. Min Act: -0.1700
Data Index: 5589552 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.2884. Min Range: -14.2884
Max Act: 13.2259. Min Act: -0.1700
Data Index: 8075301 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.2884. Min Range: -14.2884
Max Act: 13.2259. Min Act: -0.1700
Data Index: 5269960 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.2884. Min Range: -14.2884
Max Act: 13.1634. Min Act: -0.1700
Data Index: 3056366 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.2884. Min Range: -14.2884
Max Act: 13.1009. Min Act: -0.1700
Data Index: 3530687 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.2884. Min Range: -14.2884
Max Act: 13.1009. Min Act: -0.1700
Data Index: 4633791 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.2884. Min Range: -14.2884
Max Act: 13.0384. Min Act: -0.1700
Data Index: 8366678 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.2884. Min Range: -14.2884
Max Act: 13.0384. Min Act: -0.1700
Data Index: 1282719 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.2884. Min Range: -14.2884
Max Act: 13.0384. Min Act: -0.1700
Data Index: 1904570 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.2884. Min Range: -14.2884
Max Act: 12.9759. Min Act: -0.1700
Data Index: 8327948 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.2884. Min Range: -14.2884
Max Act: 12.9759. Min Act: -0.1700
Data Index: 1410537 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.2884. Min Range: -14.2884
Max Act: 12.9759. Min Act: -0.1700
Data Index: 7571500 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19