Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3076 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5024. Min Range: -10.5024
Max Act: 10.5024. Min Act: -0.1700
Data Index: 5824727 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5024. Min Range: -10.5024
Max Act: 10.3149. Min Act: -0.1700
Data Index: 4630724 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5024. Min Range: -10.5024
Max Act: 9.9399. Min Act: -0.1700
Data Index: 3240639 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5024. Min Range: -10.5024
Max Act: 9.9399. Min Act: -0.1700
Data Index: 4992306 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5024. Min Range: -10.5024
Max Act: 9.9399. Min Act: -0.1700
Data Index: 7756191 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5024. Min Range: -10.5024
Max Act: 9.9399. Min Act: -0.1700
Data Index: 6521447 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5024. Min Range: -10.5024
Max Act: 9.8774. Min Act: -0.1700
Data Index: 3025250 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5024. Min Range: -10.5024
Max Act: 9.8774. Min Act: -0.1700
Data Index: 6521445 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5024. Min Range: -10.5024
Max Act: 9.8774. Min Act: -0.1700
Data Index: 3899356 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5024. Min Range: -10.5024
Max Act: 9.8774. Min Act: -0.1700
Data Index: 6521446 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5024. Min Range: -10.5024
Max Act: 9.8149. Min Act: -0.1700
Data Index: 5537580 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5024. Min Range: -10.5024
Max Act: 9.8149. Min Act: -0.1700
Data Index: 1935533 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5024. Min Range: -10.5024
Max Act: 9.8149. Min Act: -0.1700
Data Index: 5537576 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5024. Min Range: -10.5024
Max Act: 9.7524. Min Act: -0.1700
Data Index: 1284593 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5024. Min Range: -10.5024
Max Act: 9.7524. Min Act: -0.1700
Data Index: 6521443 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5024. Min Range: -10.5024
Max Act: 9.6899. Min Act: -0.1700
Data Index: 4152479 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5024. Min Range: -10.5024
Max Act: 9.6274. Min Act: -0.1700
Data Index: 7911871 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5024. Min Range: -10.5024
Max Act: 9.6274. Min Act: -0.1700
Data Index: 7221509 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5024. Min Range: -10.5024
Max Act: 9.6274. Min Act: -0.1700
Data Index: 8694964 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5024. Min Range: -10.5024
Max Act: 9.5649. Min Act: -0.1700
Data Index: 4402036 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19