Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1388 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.9947. Min Act: -0.1700
Data Index: 4439056 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.9634. Min Act: -0.1700
Data Index: 8505493 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.9009. Min Act: -0.1700
Data Index: 2433762 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.8384. Min Act: -0.1700
Data Index: 3989903 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.8072. Min Act: -0.1700
Data Index: 3656869 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.6822. Min Act: -0.1700
Data Index: 5141212 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.6197. Min Act: -0.1700
Data Index: 3438611 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.5884. Min Act: -0.1700
Data Index: 6304961 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.5259. Min Act: -0.1700
Data Index: 1807886 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.4947. Min Act: -0.1700
Data Index: 2006743 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.4947. Min Act: -0.1700
Data Index: 2974282 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.4009. Min Act: -0.1700
Data Index: 6364846 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.3697. Min Act: -0.1700
Data Index: 6418282 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.3697. Min Act: -0.1700
Data Index: 5000005 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.3384. Min Act: -0.1700
Data Index: 7876183 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.2759. Min Act: -0.1700
Data Index: 396468 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.2759. Min Act: -0.1700
Data Index: 6149575 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.2447. Min Act: -0.1700
Data Index: 5578638 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.2447. Min Act: -0.1700
Data Index: 288394 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9947. Min Range: -6.9947
Max Act: 6.2447. Min Act: -0.1700
Data Index: 2032586 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19