Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3332 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1335. Min Range: -4.1335
Max Act: 4.1335. Min Act: -0.1700
Data Index: 6858600 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1335. Min Range: -4.1335
Max Act: 4.0397. Min Act: -0.1700
Data Index: 8133848 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1335. Min Range: -4.1335
Max Act: 4.0397. Min Act: -0.1700
Data Index: 6581665 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1335. Min Range: -4.1335
Max Act: 4.0709. Min Act: -0.1700
Data Index: 839208 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1335. Min Range: -4.1335
Max Act: 4.0084. Min Act: -0.1700
Data Index: 689700 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1335. Min Range: -4.1335
Max Act: 4.0084. Min Act: -0.1700
Data Index: 3846254 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1335. Min Range: -4.1335
Max Act: 3.9772. Min Act: -0.1700
Data Index: 7660609 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1335. Min Range: -4.1335
Max Act: 3.9772. Min Act: -0.1700
Data Index: 4886570 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1335. Min Range: -4.1335
Max Act: 3.9772. Min Act: -0.1700
Data Index: 4158220 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1335. Min Range: -4.1335
Max Act: 3.9772. Min Act: -0.1700
Data Index: 4315551 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1335. Min Range: -4.1335
Max Act: 3.9615. Min Act: -0.1700
Data Index: 1154421 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1335. Min Range: -4.1335
Max Act: 3.9615. Min Act: -0.1700
Data Index: 8825150 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1335. Min Range: -4.1335
Max Act: 3.9772. Min Act: -0.1700
Data Index: 3030685 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1335. Min Range: -4.1335
Max Act: 3.9459. Min Act: -0.1700
Data Index: 1892780 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1335. Min Range: -4.1335
Max Act: 3.9459. Min Act: -0.1700
Data Index: 387231 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1335. Min Range: -4.1335
Max Act: 3.9459. Min Act: -0.1700
Data Index: 6770228 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1335. Min Range: -4.1335
Max Act: 3.9303. Min Act: -0.1700
Data Index: 4906540 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1335. Min Range: -4.1335
Max Act: 3.9146. Min Act: -0.1700
Data Index: 1508876 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1335. Min Range: -4.1335
Max Act: 3.9459. Min Act: -0.1700
Data Index: 4184679 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1335. Min Range: -4.1335
Max Act: 3.9459. Min Act: -0.1700
Data Index: 1224747 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19