Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2596 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9069. Min Range: -7.9069
Max Act: 7.9069. Min Act: -0.1700
Data Index: 1873125 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9069. Min Range: -7.9069
Max Act: 7.5319. Min Act: -0.1700
Data Index: 6951616 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9069. Min Range: -7.9069
Max Act: 7.4069. Min Act: -0.1700
Data Index: 2095595 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9069. Min Range: -7.9069
Max Act: 7.3444. Min Act: -0.1700
Data Index: 51425 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9069. Min Range: -7.9069
Max Act: 7.3132. Min Act: -0.1700
Data Index: 7686866 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9069. Min Range: -7.9069
Max Act: 7.2819. Min Act: -0.1700
Data Index: 698206 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9069. Min Range: -7.9069
Max Act: 7.2819. Min Act: -0.1700
Data Index: 8409669 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9069. Min Range: -7.9069
Max Act: 7.2194. Min Act: -0.1700
Data Index: 7598822 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9069. Min Range: -7.9069
Max Act: 7.2194. Min Act: -0.1700
Data Index: 1402160 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9069. Min Range: -7.9069
Max Act: 7.2194. Min Act: -0.1700
Data Index: 8445981 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9069. Min Range: -7.9069
Max Act: 7.2194. Min Act: -0.1700
Data Index: 3550387 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9069. Min Range: -7.9069
Max Act: 7.2194. Min Act: -0.1700
Data Index: 5685604 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9069. Min Range: -7.9069
Max Act: 7.1882. Min Act: -0.1700
Data Index: 7540786 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9069. Min Range: -7.9069
Max Act: 7.1882. Min Act: -0.1700
Data Index: 4869292 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9069. Min Range: -7.9069
Max Act: 7.2194. Min Act: -0.1700
Data Index: 5475690 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9069. Min Range: -7.9069
Max Act: 7.1569. Min Act: -0.1700
Data Index: 8507899 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9069. Min Range: -7.9069
Max Act: 7.1569. Min Act: -0.1700
Data Index: 4687824 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9069. Min Range: -7.9069
Max Act: 7.1569. Min Act: -0.1700
Data Index: 2593875 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9069. Min Range: -7.9069
Max Act: 7.1257. Min Act: -0.1700
Data Index: 424846 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9069. Min Range: -7.9069
Max Act: 7.1257. Min Act: -0.1700
Data Index: 542215 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #19