Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 98 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2193. Min Range: -8.2193
Max Act: 8.2193. Min Act: -0.1700
Data Index: 6589546 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2193. Min Range: -8.2193
Max Act: 8.1568. Min Act: -0.1700
Data Index: 1922201 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2193. Min Range: -8.2193
Max Act: 8.0943. Min Act: -0.1700
Data Index: 4465065 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2193. Min Range: -8.2193
Max Act: 8.0318. Min Act: -0.1700
Data Index: 7447001 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2193. Min Range: -8.2193
Max Act: 8.0318. Min Act: -0.1700
Data Index: 5753296 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2193. Min Range: -8.2193
Max Act: 8.0318. Min Act: -0.1700
Data Index: 4204397 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2193. Min Range: -8.2193
Max Act: 8.0318. Min Act: -0.1700
Data Index: 598394 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2193. Min Range: -8.2193
Max Act: 7.9693. Min Act: -0.1700
Data Index: 7386817 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2193. Min Range: -8.2193
Max Act: 7.9068. Min Act: -0.1700
Data Index: 2420396 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2193. Min Range: -8.2193
Max Act: 7.9068. Min Act: -0.1700
Data Index: 2888554 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2193. Min Range: -8.2193
Max Act: 7.8443. Min Act: -0.1700
Data Index: 1009454 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2193. Min Range: -8.2193
Max Act: 7.9068. Min Act: -0.1700
Data Index: 8104820 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2193. Min Range: -8.2193
Max Act: 7.8443. Min Act: -0.1700
Data Index: 3480425 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2193. Min Range: -8.2193
Max Act: 7.9068. Min Act: -0.1700
Data Index: 1055086 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2193. Min Range: -8.2193
Max Act: 7.9068. Min Act: -0.1700
Data Index: 2190318 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2193. Min Range: -8.2193
Max Act: 7.8443. Min Act: -0.1700
Data Index: 4439747 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2193. Min Range: -8.2193
Max Act: 7.7818. Min Act: -0.1700
Data Index: 6176920 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2193. Min Range: -8.2193
Max Act: 7.8443. Min Act: -0.1700
Data Index: 2272762 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2193. Min Range: -8.2193
Max Act: 7.8443. Min Act: -0.1700
Data Index: 5932235 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2193. Min Range: -8.2193
Max Act: 7.8443. Min Act: -0.1700
Data Index: 5075171 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #19