Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3464 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0209. Min Range: -6.0209
Max Act: 6.0209. Min Act: -0.1700
Data Index: 1352951 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0209. Min Range: -6.0209
Max Act: 5.9584. Min Act: -0.1700
Data Index: 11415 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0209. Min Range: -6.0209
Max Act: 5.8647. Min Act: -0.1700
Data Index: 6093031 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0209. Min Range: -6.0209
Max Act: 5.8334. Min Act: -0.1700
Data Index: 1352952 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0209. Min Range: -6.0209
Max Act: 5.8022. Min Act: -0.1700
Data Index: 2665952 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0209. Min Range: -6.0209
Max Act: 5.7084. Min Act: -0.1700
Data Index: 314527 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0209. Min Range: -6.0209
Max Act: 5.7084. Min Act: -0.1700
Data Index: 4591576 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0209. Min Range: -6.0209
Max Act: 5.7084. Min Act: -0.1700
Data Index: 7066108 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0209. Min Range: -6.0209
Max Act: 5.7084. Min Act: -0.1700
Data Index: 5179043 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0209. Min Range: -6.0209
Max Act: 5.6772. Min Act: -0.1700
Data Index: 5192796 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0209. Min Range: -6.0209
Max Act: 5.6772. Min Act: -0.1700
Data Index: 1352949 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0209. Min Range: -6.0209
Max Act: 5.6772. Min Act: -0.1700
Data Index: 2366676 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0209. Min Range: -6.0209
Max Act: 5.6772. Min Act: -0.1700
Data Index: 339709 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0209. Min Range: -6.0209
Max Act: 5.6772. Min Act: -0.1700
Data Index: 1352954 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0209. Min Range: -6.0209
Max Act: 5.6772. Min Act: -0.1700
Data Index: 452407 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0209. Min Range: -6.0209
Max Act: 5.6459. Min Act: -0.1700
Data Index: 2741391 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0209. Min Range: -6.0209
Max Act: 5.6147. Min Act: -0.1700
Data Index: 6656408 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0209. Min Range: -6.0209
Max Act: 5.5834. Min Act: -0.1700
Data Index: 2782199 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0209. Min Range: -6.0209
Max Act: 5.5834. Min Act: -0.1700
Data Index: 5971333 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0209. Min Range: -6.0209
Max Act: 5.5834. Min Act: -0.1700
Data Index: 314528 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19