Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3066 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2291. Min Range: -3.2291
Max Act: 3.2291. Min Act: -0.1700
Data Index: 6201526 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2291. Min Range: -3.2291
Max Act: 3.1190. Min Act: -0.1700
Data Index: 3575152 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2291. Min Range: -3.2291
Max Act: 3.1032. Min Act: -0.1700
Data Index: 5295343 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2291. Min Range: -3.2291
Max Act: 3.0874. Min Act: -0.1700
Data Index: 6951347 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2291. Min Range: -3.2291
Max Act: 3.0401. Min Act: -0.1700
Data Index: 3365015 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2291. Min Range: -3.2291
Max Act: 3.0559. Min Act: -0.1700
Data Index: 1700713 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2291. Min Range: -3.2291
Max Act: 3.0243. Min Act: -0.1700
Data Index: 7339315 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2291. Min Range: -3.2291
Max Act: 2.9927. Min Act: -0.1700
Data Index: 7784799 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2291. Min Range: -3.2291
Max Act: 3.0085. Min Act: -0.1700
Data Index: 8466879 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2291. Min Range: -3.2291
Max Act: 2.9769. Min Act: -0.1700
Data Index: 1724203 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2291. Min Range: -3.2291
Max Act: 2.9927. Min Act: -0.1700
Data Index: 3804017 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2291. Min Range: -3.2291
Max Act: 2.9769. Min Act: -0.1700
Data Index: 6908827 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2291. Min Range: -3.2291
Max Act: 2.9611. Min Act: -0.1700
Data Index: 6611978 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2291. Min Range: -3.2291
Max Act: 2.9769. Min Act: -0.1700
Data Index: 4247039 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2291. Min Range: -3.2291
Max Act: 2.9769. Min Act: -0.1700
Data Index: 5302258 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2291. Min Range: -3.2291
Max Act: 2.9769. Min Act: -0.1700
Data Index: 2472550 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2291. Min Range: -3.2291
Max Act: 2.9611. Min Act: -0.1700
Data Index: 8063845 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2291. Min Range: -3.2291
Max Act: 2.9769. Min Act: -0.1700
Data Index: 8147024 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2291. Min Range: -3.2291
Max Act: 2.9611. Min Act: -0.1700
Data Index: 7015616 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2291. Min Range: -3.2291
Max Act: 2.9611. Min Act: -0.1700
Data Index: 1581118 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #19