Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4352 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1168. Min Range: -7.1168
Max Act: 7.1168. Min Act: -0.1700
Data Index: 4957243 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1168. Min Range: -7.1168
Max Act: 7.1168. Min Act: -0.1700
Data Index: 6842424 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1168. Min Range: -7.1168
Max Act: 7.0856. Min Act: -0.1700
Data Index: 6980725 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1168. Min Range: -7.1168
Max Act: 6.8356. Min Act: -0.1700
Data Index: 1227122 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1168. Min Range: -7.1168
Max Act: 6.8356. Min Act: -0.1700
Data Index: 7484656 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1168. Min Range: -7.1168
Max Act: 6.8668. Min Act: -0.1700
Data Index: 2678617 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1168. Min Range: -7.1168
Max Act: 6.7731. Min Act: -0.1700
Data Index: 1734476 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1168. Min Range: -7.1168
Max Act: 6.7731. Min Act: -0.1700
Data Index: 1413856 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1168. Min Range: -7.1168
Max Act: 6.7418. Min Act: -0.1700
Data Index: 7391682 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1168. Min Range: -7.1168
Max Act: 6.7418. Min Act: -0.1700
Data Index: 7669544 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1168. Min Range: -7.1168
Max Act: 6.7418. Min Act: -0.1700
Data Index: 6532802 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1168. Min Range: -7.1168
Max Act: 6.7106. Min Act: -0.1700
Data Index: 3199755 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1168. Min Range: -7.1168
Max Act: 6.6793. Min Act: -0.1700
Data Index: 786673 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1168. Min Range: -7.1168
Max Act: 6.6481. Min Act: -0.1700
Data Index: 28128 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1168. Min Range: -7.1168
Max Act: 6.6481. Min Act: -0.1700
Data Index: 3688468 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1168. Min Range: -7.1168
Max Act: 6.6481. Min Act: -0.1700
Data Index: 4378823 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1168. Min Range: -7.1168
Max Act: 6.6168. Min Act: -0.1700
Data Index: 5263951 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1168. Min Range: -7.1168
Max Act: 6.6168. Min Act: -0.1700
Data Index: 3415473 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1168. Min Range: -7.1168
Max Act: 6.6168. Min Act: -0.1700
Data Index: 7871538 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1168. Min Range: -7.1168
Max Act: 6.5856. Min Act: -0.1700
Data Index: 5970495 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19