Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4893 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.8197. Min Act: -0.1700
Data Index: 3097158 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.7259. Min Act: -0.1700
Data Index: 3937907 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.6634. Min Act: -0.1700
Data Index: 5199100 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.6322. Min Act: -0.1700
Data Index: 8773242 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.5072. Min Act: -0.1700
Data Index: 4481803 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.4759. Min Act: -0.1700
Data Index: 5100428 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.4759. Min Act: -0.1700
Data Index: 7770707 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.4759. Min Act: -0.1700
Data Index: 6691923 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.4447. Min Act: -0.1700
Data Index: 6944659 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.4134. Min Act: -0.1700
Data Index: 4503564 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.3509. Min Act: -0.1700
Data Index: 5331835 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.3509. Min Act: -0.1700
Data Index: 5305295 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.3197. Min Act: -0.1700
Data Index: 6235939 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.2884. Min Act: -0.1700
Data Index: 7162755 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.2572. Min Act: -0.1700
Data Index: 1428412 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.2572. Min Act: -0.1700
Data Index: 8348477 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.2572. Min Act: -0.1700
Data Index: 3672274 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.2572. Min Act: -0.1700
Data Index: 5084112 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.2572. Min Act: -0.1700
Data Index: 3715544 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8197. Min Range: -7.8197
Max Act: 7.2572. Min Act: -0.1700
Data Index: 597611 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #19