Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3895 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4679. Min Range: -5.4679
Max Act: 5.4679. Min Act: -0.1700
Data Index: 2624942 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4679. Min Range: -5.4679
Max Act: 5.4367. Min Act: -0.1700
Data Index: 4352038 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4679. Min Range: -5.4679
Max Act: 5.4367. Min Act: -0.1700
Data Index: 5651567 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4679. Min Range: -5.4679
Max Act: 5.4054. Min Act: -0.1700
Data Index: 2624940 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4679. Min Range: -5.4679
Max Act: 5.4367. Min Act: -0.1700
Data Index: 2879919 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4679. Min Range: -5.4679
Max Act: 5.4054. Min Act: -0.1700
Data Index: 363590 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4679. Min Range: -5.4679
Max Act: 5.4367. Min Act: -0.1697
Data Index: 3475558 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4679. Min Range: -5.4679
Max Act: 5.4054. Min Act: -0.1700
Data Index: 2624932 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4679. Min Range: -5.4679
Max Act: 5.4367. Min Act: -0.1700
Data Index: 5876467 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4679. Min Range: -5.4679
Max Act: 5.4367. Min Act: -0.1700
Data Index: 8285036 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4679. Min Range: -5.4679
Max Act: 5.4367. Min Act: -0.1700
Data Index: 3181386 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4679. Min Range: -5.4679
Max Act: 5.4367. Min Act: -0.1700
Data Index: 2932212 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4679. Min Range: -5.4679
Max Act: 5.4367. Min Act: -0.1700
Data Index: 4280837 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4679. Min Range: -5.4679
Max Act: 5.4367. Min Act: -0.1700
Data Index: 2187183 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4679. Min Range: -5.4679
Max Act: 5.4367. Min Act: -0.1700
Data Index: 4584315 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4679. Min Range: -5.4679
Max Act: 5.4367. Min Act: -0.1700
Data Index: 6851231 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4679. Min Range: -5.4679
Max Act: 5.4367. Min Act: -0.1700
Data Index: 6861624 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4679. Min Range: -5.4679
Max Act: 5.4367. Min Act: -0.1700
Data Index: 2624933 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4679. Min Range: -5.4679
Max Act: 5.4367. Min Act: -0.1700
Data Index: 6729590 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4679. Min Range: -5.4679
Max Act: 5.4367. Min Act: -0.1700
Data Index: 306474 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19