Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6017 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.8432. Min Act: -0.1700
Data Index: 6636055 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.8120. Min Act: -0.1700
Data Index: 7272799 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.7494. Min Act: -0.1700
Data Index: 4758885 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.7494. Min Act: -0.1700
Data Index: 7204288 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.7181. Min Act: -0.1700
Data Index: 5713489 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.6869. Min Act: -0.1700
Data Index: 4284843 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.6869. Min Act: -0.1700
Data Index: 96110 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.6712. Min Act: -0.1700
Data Index: 4152782 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.6556. Min Act: -0.1700
Data Index: 3655238 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.6556. Min Act: -0.1700
Data Index: 3499372 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.6556. Min Act: -0.1700
Data Index: 4351504 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.6556. Min Act: -0.1700
Data Index: 5673541 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.6556. Min Act: -0.1700
Data Index: 4129620 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.6399. Min Act: -0.1700
Data Index: 1084319 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.6243. Min Act: -0.1700
Data Index: 3302987 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.6399. Min Act: -0.1700
Data Index: 2525370 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.6243. Min Act: -0.1700
Data Index: 1399496 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.6243. Min Act: -0.1700
Data Index: 5948751 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.6243. Min Act: -0.1700
Data Index: 160459 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.6243. Min Act: -0.1700
Data Index: 416226 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19