Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3110 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.7507. Min Act: -0.1700
Data Index: 1773547 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.7194. Min Act: -0.1700
Data Index: 4580982 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.6257. Min Act: -0.1700
Data Index: 1800096 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.6257. Min Act: -0.1700
Data Index: 349617 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.5944. Min Act: -0.1700
Data Index: 5103957 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.5632. Min Act: -0.1700
Data Index: 3223399 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.5319. Min Act: -0.1700
Data Index: 2271531 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.5319. Min Act: -0.1700
Data Index: 5049098 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.5319. Min Act: -0.1700
Data Index: 1319682 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.5319. Min Act: -0.1700
Data Index: 6094298 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.5007. Min Act: -0.1700
Data Index: 7034072 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4694. Min Act: -0.1700
Data Index: 7499426 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4694. Min Act: -0.1700
Data Index: 1522656 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4694. Min Act: -0.1700
Data Index: 330794 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4382. Min Act: -0.1700
Data Index: 927038 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4069. Min Act: -0.1700
Data Index: 3557695 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4069. Min Act: -0.1700
Data Index: 398727 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4069. Min Act: -0.1700
Data Index: 5763062 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4069. Min Act: -0.1700
Data Index: 3246823 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7507. Min Range: -4.7507
Max Act: 4.4069. Min Act: -0.1700
Data Index: 4706675 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19