Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5401 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7500. Min Range: -4.7500
Max Act: 4.7500. Min Act: -0.1700
Data Index: 587607 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7500. Min Range: -4.7500
Max Act: 4.4375. Min Act: -0.1700
Data Index: 6911590 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7500. Min Range: -4.7500
Max Act: 4.4063. Min Act: -0.1700
Data Index: 3253531 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7500. Min Range: -4.7500
Max Act: 4.3750. Min Act: -0.1700
Data Index: 7289379 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7500. Min Range: -4.7500
Max Act: 4.3750. Min Act: -0.1700
Data Index: 4604204 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7500. Min Range: -4.7500
Max Act: 4.3438. Min Act: -0.1700
Data Index: 1291428 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7500. Min Range: -4.7500
Max Act: 4.3438. Min Act: -0.1700
Data Index: 3985621 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7500. Min Range: -4.7500
Max Act: 4.3125. Min Act: -0.1700
Data Index: 288923 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7500. Min Range: -4.7500
Max Act: 4.2813. Min Act: -0.1700
Data Index: 2444940 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7500. Min Range: -4.7500
Max Act: 4.2500. Min Act: -0.1700
Data Index: 1947226 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7500. Min Range: -4.7500
Max Act: 4.2500. Min Act: -0.1700
Data Index: 84298 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7500. Min Range: -4.7500
Max Act: 4.2813. Min Act: -0.1700
Data Index: 70297 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7500. Min Range: -4.7500
Max Act: 4.2500. Min Act: -0.1700
Data Index: 8800292 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7500. Min Range: -4.7500
Max Act: 4.2500. Min Act: -0.1700
Data Index: 6953309 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7500. Min Range: -4.7500
Max Act: 4.2500. Min Act: -0.1700
Data Index: 4317352 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7500. Min Range: -4.7500
Max Act: 4.2500. Min Act: -0.1700
Data Index: 444482 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7500. Min Range: -4.7500
Max Act: 4.2500. Min Act: -0.1700
Data Index: 7893467 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7500. Min Range: -4.7500
Max Act: 4.2500. Min Act: -0.1700
Data Index: 2618131 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7500. Min Range: -4.7500
Max Act: 4.2188. Min Act: -0.1700
Data Index: 4633252 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7500. Min Range: -4.7500
Max Act: 4.2188. Min Act: -0.1700
Data Index: 7688895 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19