Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3871 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4531. Min Range: -7.4531
Max Act: 7.4531. Min Act: -0.1700
Data Index: 5416273 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4531. Min Range: -7.4531
Max Act: 7.3281. Min Act: -0.1700
Data Index: 3357936 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4531. Min Range: -7.4531
Max Act: 7.2969. Min Act: -0.1700
Data Index: 5070845 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4531. Min Range: -7.4531
Max Act: 7.2656. Min Act: -0.1700
Data Index: 6449328 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4531. Min Range: -7.4531
Max Act: 7.2031. Min Act: -0.1700
Data Index: 3584217 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4531. Min Range: -7.4531
Max Act: 7.1719. Min Act: -0.1700
Data Index: 5838925 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4531. Min Range: -7.4531
Max Act: 7.1406. Min Act: -0.1700
Data Index: 5978666 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4531. Min Range: -7.4531
Max Act: 7.1094. Min Act: -0.1700
Data Index: 5878835 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4531. Min Range: -7.4531
Max Act: 7.0469. Min Act: -0.1700
Data Index: 8795142 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4531. Min Range: -7.4531
Max Act: 7.0469. Min Act: -0.1700
Data Index: 4772916 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4531. Min Range: -7.4531
Max Act: 6.9844. Min Act: -0.1700
Data Index: 8281009 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4531. Min Range: -7.4531
Max Act: 6.9219. Min Act: -0.1700
Data Index: 442587 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4531. Min Range: -7.4531
Max Act: 6.9219. Min Act: -0.1700
Data Index: 3239075 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4531. Min Range: -7.4531
Max Act: 6.8906. Min Act: -0.1700
Data Index: 1807120 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4531. Min Range: -7.4531
Max Act: 6.8906. Min Act: -0.1700
Data Index: 2005093 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4531. Min Range: -7.4531
Max Act: 6.8906. Min Act: -0.1700
Data Index: 2191342 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4531. Min Range: -7.4531
Max Act: 6.8281. Min Act: -0.1700
Data Index: 7104536 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4531. Min Range: -7.4531
Max Act: 6.8594. Min Act: -0.1700
Data Index: 1856598 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4531. Min Range: -7.4531
Max Act: 6.8281. Min Act: -0.1700
Data Index: 3913622 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4531. Min Range: -7.4531
Max Act: 6.8281. Min Act: -0.1700
Data Index: 3363336 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19