Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2647 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8460. Min Range: -7.8460
Max Act: 7.8460. Min Act: -0.1700
Data Index: 3921970 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8460. Min Range: -7.8460
Max Act: 7.8460. Min Act: -0.1700
Data Index: 5646982 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8460. Min Range: -7.8460
Max Act: 7.8460. Min Act: -0.1700
Data Index: 5954935 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8460. Min Range: -7.8460
Max Act: 7.7835. Min Act: -0.1700
Data Index: 7232347 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8460. Min Range: -7.8460
Max Act: 7.7835. Min Act: -0.1700
Data Index: 576821 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8460. Min Range: -7.8460
Max Act: 7.8460. Min Act: -0.1700
Data Index: 2601819 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8460. Min Range: -7.8460
Max Act: 7.7835. Min Act: -0.1700
Data Index: 8128237 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8460. Min Range: -7.8460
Max Act: 7.7835. Min Act: -0.1700
Data Index: 5777326 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8460. Min Range: -7.8460
Max Act: 7.7210. Min Act: -0.1700
Data Index: 111257 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8460. Min Range: -7.8460
Max Act: 7.7210. Min Act: -0.1700
Data Index: 4112501 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8460. Min Range: -7.8460
Max Act: 7.6585. Min Act: -0.1700
Data Index: 3483966 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8460. Min Range: -7.8460
Max Act: 7.5960. Min Act: -0.1700
Data Index: 1687538 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8460. Min Range: -7.8460
Max Act: 7.5960. Min Act: -0.1700
Data Index: 8763630 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8460. Min Range: -7.8460
Max Act: 7.6585. Min Act: -0.1700
Data Index: 5353398 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8460. Min Range: -7.8460
Max Act: 7.6585. Min Act: -0.1700
Data Index: 798392 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8460. Min Range: -7.8460
Max Act: 7.7210. Min Act: -0.1700
Data Index: 7778141 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8460. Min Range: -7.8460
Max Act: 7.6585. Min Act: -0.1700
Data Index: 5788809 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8460. Min Range: -7.8460
Max Act: 7.6585. Min Act: -0.1700
Data Index: 3515967 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8460. Min Range: -7.8460
Max Act: 7.5960. Min Act: -0.1700
Data Index: 2659474 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8460. Min Range: -7.8460
Max Act: 7.5960. Min Act: -0.1700
Data Index: 8590658 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #19