Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 923 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6247. Min Range: -2.6247
Max Act: 2.6247. Min Act: -0.1700
Data Index: 3901165 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6247. Min Range: -2.6247
Max Act: 2.5925. Min Act: -0.1700
Data Index: 3561381 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6247. Min Range: -2.6247
Max Act: 2.5764. Min Act: -0.1700
Data Index: 7141320 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6247. Min Range: -2.6247
Max Act: 2.5764. Min Act: -0.1700
Data Index: 548073 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6247. Min Range: -2.6247
Max Act: 2.5280. Min Act: -0.1700
Data Index: 311137 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6247. Min Range: -2.6247
Max Act: 2.4956. Min Act: -0.1700
Data Index: 562537 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6247. Min Range: -2.6247
Max Act: 2.4632. Min Act: -0.1700
Data Index: 4758474 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6247. Min Range: -2.6247
Max Act: 2.5118. Min Act: -0.1700
Data Index: 7507793 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6247. Min Range: -2.6247
Max Act: 2.5118. Min Act: -0.1700
Data Index: 3974703 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6247. Min Range: -2.6247
Max Act: 2.4956. Min Act: -0.1700
Data Index: 2199748 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6247. Min Range: -2.6247
Max Act: 2.4794. Min Act: -0.1700
Data Index: 6917628 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6247. Min Range: -2.6247
Max Act: 2.4956. Min Act: -0.1700
Data Index: 5678893 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6247. Min Range: -2.6247
Max Act: 2.4632. Min Act: -0.1700
Data Index: 8341675 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6247. Min Range: -2.6247
Max Act: 2.4794. Min Act: -0.1700
Data Index: 5962453 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6247. Min Range: -2.6247
Max Act: 2.4469. Min Act: -0.1700
Data Index: 545231 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6247. Min Range: -2.6247
Max Act: 2.4143. Min Act: -0.1700
Data Index: 3074295 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6247. Min Range: -2.6247
Max Act: 2.4469. Min Act: -0.1700
Data Index: 1573640 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6247. Min Range: -2.6247
Max Act: 2.4469. Min Act: -0.1700
Data Index: 7739821 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6247. Min Range: -2.6247
Max Act: 2.4306. Min Act: -0.1700
Data Index: 6232558 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6247. Min Range: -2.6247
Max Act: 2.4306. Min Act: -0.1700
Data Index: 744636 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19