Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4003 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1316. Min Range: -4.1316
Max Act: 4.1316. Min Act: -0.1700
Data Index: 2981328 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1316. Min Range: -4.1316
Max Act: 3.9441. Min Act: -0.1700
Data Index: 3074762 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1316. Min Range: -4.1316
Max Act: 3.9441. Min Act: -0.1700
Data Index: 2981327 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1316. Min Range: -4.1316
Max Act: 3.8503. Min Act: -0.1700
Data Index: 4490084 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1316. Min Range: -4.1316
Max Act: 3.8190. Min Act: -0.1700
Data Index: 4754287 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1316. Min Range: -4.1316
Max Act: 3.8503. Min Act: -0.1700
Data Index: 4754301 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1316. Min Range: -4.1316
Max Act: 3.7877. Min Act: -0.1700
Data Index: 8766256 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1316. Min Range: -4.1316
Max Act: 3.7877. Min Act: -0.1700
Data Index: 5440001 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1316. Min Range: -4.1316
Max Act: 3.7877. Min Act: -0.1700
Data Index: 468320 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1316. Min Range: -4.1316
Max Act: 3.8190. Min Act: -0.1700
Data Index: 7393592 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1316. Min Range: -4.1316
Max Act: 3.8190. Min Act: -0.1700
Data Index: 7393589 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1316. Min Range: -4.1316
Max Act: 3.7565. Min Act: -0.1700
Data Index: 3441131 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1316. Min Range: -4.1316
Max Act: 3.7565. Min Act: -0.1700
Data Index: 3867737 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1316. Min Range: -4.1316
Max Act: 3.7565. Min Act: -0.1700
Data Index: 3441130 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1316. Min Range: -4.1316
Max Act: 3.7565. Min Act: -0.1700
Data Index: 7618219 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1316. Min Range: -4.1316
Max Act: 3.7565. Min Act: -0.1700
Data Index: 1487382 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1316. Min Range: -4.1316
Max Act: 3.7252. Min Act: -0.1700
Data Index: 5603690 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1316. Min Range: -4.1316
Max Act: 3.7252. Min Act: -0.1700
Data Index: 699670 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1316. Min Range: -4.1316
Max Act: 3.7252. Min Act: -0.1700
Data Index: 2067344 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1316. Min Range: -4.1316
Max Act: 3.7252. Min Act: -0.1700
Data Index: 5535725 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19