Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 14 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1583. Min Range: -4.1583
Max Act: 4.1583. Min Act: -0.1700
Data Index: 1664363 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1583. Min Range: -4.1583
Max Act: 4.0958. Min Act: -0.1700
Data Index: 2058657 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1583. Min Range: -4.1583
Max Act: 3.9864. Min Act: -0.1700
Data Index: 1681430 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1583. Min Range: -4.1583
Max Act: 3.8457. Min Act: -0.1700
Data Index: 6559581 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1583. Min Range: -4.1583
Max Act: 3.7988. Min Act: -0.1700
Data Index: 7414394 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1583. Min Range: -4.1583
Max Act: 3.7675. Min Act: -0.1700
Data Index: 5057830 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1583. Min Range: -4.1583
Max Act: 3.7518. Min Act: -0.1700
Data Index: 1210339 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1583. Min Range: -4.1583
Max Act: 3.7206. Min Act: -0.1700
Data Index: 686379 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1583. Min Range: -4.1583
Max Act: 3.7206. Min Act: -0.1700
Data Index: 5006773 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1583. Min Range: -4.1583
Max Act: 3.7049. Min Act: -0.1700
Data Index: 8300543 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1583. Min Range: -4.1583
Max Act: 3.7049. Min Act: -0.1700
Data Index: 2651789 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1583. Min Range: -4.1583
Max Act: 3.6893. Min Act: -0.1700
Data Index: 4288546 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1583. Min Range: -4.1583
Max Act: 3.6423. Min Act: -0.1700
Data Index: 1617357 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1583. Min Range: -4.1583
Max Act: 3.6267. Min Act: -0.1700
Data Index: 4777661 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1583. Min Range: -4.1583
Max Act: 3.6267. Min Act: -0.1700
Data Index: 4302410 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1583. Min Range: -4.1583
Max Act: 3.6110. Min Act: -0.1700
Data Index: 4711090 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1583. Min Range: -4.1583
Max Act: 3.6110. Min Act: -0.1700
Data Index: 3264963 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1583. Min Range: -4.1583
Max Act: 3.6110. Min Act: -0.1700
Data Index: 8661038 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1583. Min Range: -4.1583
Max Act: 3.6110. Min Act: -0.1700
Data Index: 1760048 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1583. Min Range: -4.1583
Max Act: 3.5641. Min Act: -0.1700
Data Index: 4794756 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #19