Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1485 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8263. Min Range: -3.8263
Max Act: 3.8263. Min Act: -0.1700
Data Index: 7935153 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8263. Min Range: -3.8263
Max Act: 3.8106. Min Act: -0.1700
Data Index: 7959852 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8263. Min Range: -3.8263
Max Act: 3.6699. Min Act: -0.1700
Data Index: 6122370 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8263. Min Range: -3.8263
Max Act: 3.6386. Min Act: -0.1700
Data Index: 3548326 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8263. Min Range: -3.8263
Max Act: 3.6229. Min Act: -0.1700
Data Index: 4879305 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8263. Min Range: -3.8263
Max Act: 3.6229. Min Act: -0.1700
Data Index: 8251304 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8263. Min Range: -3.8263
Max Act: 3.6386. Min Act: -0.1700
Data Index: 6382551 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8263. Min Range: -3.8263
Max Act: 3.5290. Min Act: -0.1700
Data Index: 1102747 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8263. Min Range: -3.8263
Max Act: 3.5290. Min Act: -0.1700
Data Index: 179435 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8263. Min Range: -3.8263
Max Act: 3.5290. Min Act: -0.1700
Data Index: 3793897 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8263. Min Range: -3.8263
Max Act: 3.5134. Min Act: -0.1700
Data Index: 5570851 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8263. Min Range: -3.8263
Max Act: 3.5134. Min Act: -0.1700
Data Index: 5911454 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8263. Min Range: -3.8263
Max Act: 3.4977. Min Act: -0.1700
Data Index: 7258155 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8263. Min Range: -3.8263
Max Act: 3.4820. Min Act: -0.1700
Data Index: 7343759 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8263. Min Range: -3.8263
Max Act: 3.4664. Min Act: -0.1700
Data Index: 7093680 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8263. Min Range: -3.8263
Max Act: 3.4664. Min Act: -0.1700
Data Index: 219551 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8263. Min Range: -3.8263
Max Act: 3.4507. Min Act: -0.1700
Data Index: 2289973 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8263. Min Range: -3.8263
Max Act: 3.4507. Min Act: -0.1700
Data Index: 3451497 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8263. Min Range: -3.8263
Max Act: 3.4507. Min Act: -0.1700
Data Index: 6359610 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8263. Min Range: -3.8263
Max Act: 3.4350. Min Act: -0.1700
Data Index: 937140 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19