Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3091 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0035. Min Range: -5.0035
Max Act: 5.0035. Min Act: -0.1700
Data Index: 7334144 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0035. Min Range: -5.0035
Max Act: 4.8160. Min Act: -0.1700
Data Index: 7377257 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0035. Min Range: -5.0035
Max Act: 4.8472. Min Act: -0.1700
Data Index: 6672445 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0035. Min Range: -5.0035
Max Act: 4.8472. Min Act: -0.1700
Data Index: 5642230 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0035. Min Range: -5.0035
Max Act: 4.8472. Min Act: -0.1700
Data Index: 7489082 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0035. Min Range: -5.0035
Max Act: 4.8160. Min Act: -0.1700
Data Index: 588595 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0035. Min Range: -5.0035
Max Act: 4.8472. Min Act: -0.1700
Data Index: 256012 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0035. Min Range: -5.0035
Max Act: 4.7847. Min Act: -0.1700
Data Index: 7662983 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0035. Min Range: -5.0035
Max Act: 4.7535. Min Act: -0.1700
Data Index: 8765610 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0035. Min Range: -5.0035
Max Act: 4.7535. Min Act: -0.1700
Data Index: 1562371 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0035. Min Range: -5.0035
Max Act: 4.7222. Min Act: -0.1700
Data Index: 2045727 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0035. Min Range: -5.0035
Max Act: 4.7535. Min Act: -0.1700
Data Index: 4308415 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0035. Min Range: -5.0035
Max Act: 4.7535. Min Act: -0.1700
Data Index: 357430 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0035. Min Range: -5.0035
Max Act: 4.7222. Min Act: -0.1700
Data Index: 3566368 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0035. Min Range: -5.0035
Max Act: 4.7222. Min Act: -0.1700
Data Index: 5395838 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0035. Min Range: -5.0035
Max Act: 4.7222. Min Act: -0.1700
Data Index: 6887728 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0035. Min Range: -5.0035
Max Act: 4.6910. Min Act: -0.1700
Data Index: 7975475 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0035. Min Range: -5.0035
Max Act: 4.6910. Min Act: -0.1700
Data Index: 588581 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0035. Min Range: -5.0035
Max Act: 4.7222. Min Act: -0.1700
Data Index: 891650 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0035. Min Range: -5.0035
Max Act: 4.6597. Min Act: -0.1700
Data Index: 3678479 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19