Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3317 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0394. Min Range: -5.0394
Max Act: 5.0394. Min Act: -0.1700
Data Index: 4959172 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0394. Min Range: -5.0394
Max Act: 5.0082. Min Act: -0.1700
Data Index: 4231438 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0394. Min Range: -5.0394
Max Act: 4.6644. Min Act: -0.1700
Data Index: 3784175 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0394. Min Range: -5.0394
Max Act: 4.6644. Min Act: -0.1700
Data Index: 4579367 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0394. Min Range: -5.0394
Max Act: 4.5707. Min Act: -0.1700
Data Index: 250543 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0394. Min Range: -5.0394
Max Act: 4.5707. Min Act: -0.1700
Data Index: 5001878 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0394. Min Range: -5.0394
Max Act: 4.5707. Min Act: -0.1700
Data Index: 5247474 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0394. Min Range: -5.0394
Max Act: 4.5707. Min Act: -0.1700
Data Index: 187358 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0394. Min Range: -5.0394
Max Act: 4.5082. Min Act: -0.1700
Data Index: 6016422 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0394. Min Range: -5.0394
Max Act: 4.5082. Min Act: -0.1700
Data Index: 904260 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0394. Min Range: -5.0394
Max Act: 4.4769. Min Act: -0.1700
Data Index: 2038070 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0394. Min Range: -5.0394
Max Act: 4.4769. Min Act: -0.1700
Data Index: 395652 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0394. Min Range: -5.0394
Max Act: 4.4769. Min Act: -0.1700
Data Index: 1517396 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0394. Min Range: -5.0394
Max Act: 4.4769. Min Act: -0.1700
Data Index: 5252553 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0394. Min Range: -5.0394
Max Act: 4.4769. Min Act: -0.1700
Data Index: 3151 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0394. Min Range: -5.0394
Max Act: 4.4769. Min Act: -0.1700
Data Index: 3113429 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0394. Min Range: -5.0394
Max Act: 4.4769. Min Act: -0.1700
Data Index: 3250808 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0394. Min Range: -5.0394
Max Act: 4.4769. Min Act: -0.1700
Data Index: 7544316 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0394. Min Range: -5.0394
Max Act: 4.4457. Min Act: -0.1700
Data Index: 5157345 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0394. Min Range: -5.0394
Max Act: 4.4457. Min Act: -0.1700
Data Index: 632489 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19