Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1643 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9033. Min Range: -4.9033
Max Act: 4.9033. Min Act: -0.1700
Data Index: 1749946 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9033. Min Range: -4.9033
Max Act: 4.9033. Min Act: -0.1700
Data Index: 5267196 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9033. Min Range: -4.9033
Max Act: 4.8408. Min Act: -0.1700
Data Index: 7680358 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9033. Min Range: -4.9033
Max Act: 4.8408. Min Act: -0.1700
Data Index: 130871 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9033. Min Range: -4.9033
Max Act: 4.8721. Min Act: -0.1700
Data Index: 4816887 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9033. Min Range: -4.9033
Max Act: 4.8721. Min Act: -0.1700
Data Index: 1278705 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9033. Min Range: -4.9033
Max Act: 4.8721. Min Act: -0.1700
Data Index: 8590563 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9033. Min Range: -4.9033
Max Act: 4.8096. Min Act: -0.1700
Data Index: 1620384 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9033. Min Range: -4.9033
Max Act: 4.8096. Min Act: -0.1700
Data Index: 7331618 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9033. Min Range: -4.9033
Max Act: 4.8721. Min Act: -0.1700
Data Index: 6738915 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9033. Min Range: -4.9033
Max Act: 4.8408. Min Act: -0.1700
Data Index: 8209378 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9033. Min Range: -4.9033
Max Act: 4.8408. Min Act: -0.1700
Data Index: 7691559 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9033. Min Range: -4.9033
Max Act: 4.8408. Min Act: -0.1700
Data Index: 1248394 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9033. Min Range: -4.9033
Max Act: 4.8408. Min Act: -0.1700
Data Index: 7640858 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9033. Min Range: -4.9033
Max Act: 4.8408. Min Act: -0.1700
Data Index: 2989434 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9033. Min Range: -4.9033
Max Act: 4.8096. Min Act: -0.1700
Data Index: 394867 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9033. Min Range: -4.9033
Max Act: 4.8096. Min Act: -0.1700
Data Index: 5637707 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9033. Min Range: -4.9033
Max Act: 4.7783. Min Act: -0.1700
Data Index: 7254556 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9033. Min Range: -4.9033
Max Act: 4.7783. Min Act: -0.1700
Data Index: 7576586 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9033. Min Range: -4.9033
Max Act: 4.7783. Min Act: -0.1700
Data Index: 1238404 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #19