Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6250 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3362. Min Range: -6.3362
Max Act: 6.3362. Min Act: -0.1700
Data Index: 7012264 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3362. Min Range: -6.3362
Max Act: 6.2112. Min Act: -0.1700
Data Index: 410612 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3362. Min Range: -6.3362
Max Act: 6.2112. Min Act: -0.1700
Data Index: 8380064 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3362. Min Range: -6.3362
Max Act: 6.2112. Min Act: -0.1700
Data Index: 1731588 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3362. Min Range: -6.3362
Max Act: 6.1175. Min Act: -0.1700
Data Index: 3658560 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3362. Min Range: -6.3362
Max Act: 6.0862. Min Act: -0.1700
Data Index: 2926549 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3362. Min Range: -6.3362
Max Act: 6.0550. Min Act: -0.1700
Data Index: 2706646 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.9300. Min Act: -0.1700
Data Index: 4006450 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.8987. Min Act: -0.1700
Data Index: 5020153 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.9300. Min Act: -0.1700
Data Index: 3738999 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.8987. Min Act: -0.1700
Data Index: 235426 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.8987. Min Act: -0.1700
Data Index: 6440428 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.8675. Min Act: -0.1700
Data Index: 4064121 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.8675. Min Act: -0.1700
Data Index: 4003361 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.8675. Min Act: -0.1700
Data Index: 3570540 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.8050. Min Act: -0.1700
Data Index: 7758857 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.8050. Min Act: -0.1700
Data Index: 1206277 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.7737. Min Act: -0.1700
Data Index: 324730 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.7737. Min Act: -0.1700
Data Index: 8274557 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3362. Min Range: -6.3362
Max Act: 5.7112. Min Act: -0.1700
Data Index: 7968088 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19