Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6221 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0251. Min Range: -7.0251
Max Act: 7.0251. Min Act: -0.1700
Data Index: 3054304 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0251. Min Range: -7.0251
Max Act: 6.9314. Min Act: -0.1700
Data Index: 6115494 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0251. Min Range: -7.0251
Max Act: 6.7751. Min Act: -0.1700
Data Index: 133601 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0251. Min Range: -7.0251
Max Act: 6.8064. Min Act: -0.1700
Data Index: 3405144 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0251. Min Range: -7.0251
Max Act: 6.8064. Min Act: -0.1700
Data Index: 8610470 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0251. Min Range: -7.0251
Max Act: 6.6501. Min Act: -0.1700
Data Index: 4617119 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0251. Min Range: -7.0251
Max Act: 6.5876. Min Act: -0.1700
Data Index: 4479264 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0251. Min Range: -7.0251
Max Act: 6.5876. Min Act: -0.1700
Data Index: 4892175 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0251. Min Range: -7.0251
Max Act: 6.5564. Min Act: -0.1700
Data Index: 4342257 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0251. Min Range: -7.0251
Max Act: 6.5564. Min Act: -0.1700
Data Index: 2526065 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0251. Min Range: -7.0251
Max Act: 6.5564. Min Act: -0.1700
Data Index: 1991270 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0251. Min Range: -7.0251
Max Act: 6.5564. Min Act: -0.1700
Data Index: 1457765 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0251. Min Range: -7.0251
Max Act: 6.5564. Min Act: -0.1700
Data Index: 5583542 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0251. Min Range: -7.0251
Max Act: 6.4939. Min Act: -0.1700
Data Index: 7040386 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0251. Min Range: -7.0251
Max Act: 6.4314. Min Act: -0.1700
Data Index: 3186601 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0251. Min Range: -7.0251
Max Act: 6.4626. Min Act: -0.1700
Data Index: 4719187 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0251. Min Range: -7.0251
Max Act: 6.4314. Min Act: -0.1700
Data Index: 6754545 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0251. Min Range: -7.0251
Max Act: 6.4626. Min Act: -0.1700
Data Index: 2221890 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0251. Min Range: -7.0251
Max Act: 6.4939. Min Act: -0.1700
Data Index: 3712582 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0251. Min Range: -7.0251
Max Act: 6.4626. Min Act: -0.1700
Data Index: 5353218 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19