Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1999 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9671. Min Range: -4.9671
Max Act: 4.9671. Min Act: -0.1700
Data Index: 6563428 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9671. Min Range: -4.9671
Max Act: 4.9358. Min Act: -0.1700
Data Index: 5405969 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9671. Min Range: -4.9671
Max Act: 4.9358. Min Act: -0.1700
Data Index: 6693267 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9671. Min Range: -4.9671
Max Act: 4.9358. Min Act: -0.1700
Data Index: 2758406 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9671. Min Range: -4.9671
Max Act: 4.9358. Min Act: -0.1700
Data Index: 3000896 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9671. Min Range: -4.9671
Max Act: 4.9358. Min Act: -0.1700
Data Index: 3433707 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9671. Min Range: -4.9671
Max Act: 4.8733. Min Act: -0.1700
Data Index: 1094691 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9671. Min Range: -4.9671
Max Act: 4.8733. Min Act: -0.1700
Data Index: 3356379 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9671. Min Range: -4.9671
Max Act: 4.8733. Min Act: -0.1698
Data Index: 3702030 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9671. Min Range: -4.9671
Max Act: 4.8733. Min Act: -0.1700
Data Index: 2770836 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9671. Min Range: -4.9671
Max Act: 4.8421. Min Act: -0.1700
Data Index: 6313190 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9671. Min Range: -4.9671
Max Act: 4.8421. Min Act: -0.1700
Data Index: 3241489 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9671. Min Range: -4.9671
Max Act: 4.8421. Min Act: -0.1700
Data Index: 6016333 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9671. Min Range: -4.9671
Max Act: 4.8108. Min Act: -0.1700
Data Index: 6033840 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9671. Min Range: -4.9671
Max Act: 4.8108. Min Act: -0.1700
Data Index: 3458519 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9671. Min Range: -4.9671
Max Act: 4.8108. Min Act: -0.1700
Data Index: 1682994 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9671. Min Range: -4.9671
Max Act: 4.7796. Min Act: -0.1700
Data Index: 5495659 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9671. Min Range: -4.9671
Max Act: 4.8108. Min Act: -0.1700
Data Index: 1584321 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9671. Min Range: -4.9671
Max Act: 4.8108. Min Act: -0.1700
Data Index: 5495660 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9671. Min Range: -4.9671
Max Act: 4.8108. Min Act: -0.1700
Data Index: 5480980 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #19