Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2935 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.6232. Min Range: -0.6232
Max Act: 0.6232. Min Act: -0.1700
Data Index: 629014 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6232. Min Range: -0.6232
Max Act: 0.6153. Min Act: -0.1700
Data Index: 817293 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6232. Min Range: -0.6232
Max Act: 0.6153. Min Act: -0.1700
Data Index: 796929 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6232. Min Range: -0.6232
Max Act: 0.6074. Min Act: -0.1700
Data Index: 3171654 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6232. Min Range: -0.6232
Max Act: 0.6074. Min Act: -0.1700
Data Index: 4323496 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6232. Min Range: -0.6232
Max Act: 0.5760. Min Act: -0.1700
Data Index: 4118354 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6232. Min Range: -0.6232
Max Act: 0.5838. Min Act: -0.1700
Data Index: 41341 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6232. Min Range: -0.6232
Max Act: 0.5838. Min Act: -0.1700
Data Index: 2070536 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6232. Min Range: -0.6232
Max Act: 0.5760. Min Act: -0.1700
Data Index: 304205 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6232. Min Range: -0.6232
Max Act: 0.5682. Min Act: -0.1700
Data Index: 4323502 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6232. Min Range: -0.6232
Max Act: 0.5682. Min Act: -0.1700
Data Index: 8048831 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6232. Min Range: -0.6232
Max Act: 0.5605. Min Act: -0.1700
Data Index: 6756899 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6232. Min Range: -0.6232
Max Act: 0.5528. Min Act: -0.1700
Data Index: 2179743 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6232. Min Range: -0.6232
Max Act: 0.5605. Min Act: -0.1700
Data Index: 6166980 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6232. Min Range: -0.6232
Max Act: 0.5528. Min Act: -0.1700
Data Index: 2917829 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6232. Min Range: -0.6232
Max Act: 0.5451. Min Act: -0.1700
Data Index: 4556908 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6232. Min Range: -0.6232
Max Act: 0.5451. Min Act: -0.1700
Data Index: 4074923 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6232. Min Range: -0.6232
Max Act: 0.5451. Min Act: -0.1700
Data Index: 5020276 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6232. Min Range: -0.6232
Max Act: 0.5221. Min Act: -0.1700
Data Index: 904476 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6232. Min Range: -0.6232
Max Act: 0.5297. Min Act: -0.1700
Data Index: 6996396 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19