Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5696 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0955. Min Range: -6.0955
Max Act: 6.0955. Min Act: -0.1700
Data Index: 2234921 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0955. Min Range: -6.0955
Max Act: 6.0018. Min Act: -0.1700
Data Index: 5450984 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0955. Min Range: -6.0955
Max Act: 5.9393. Min Act: -0.1700
Data Index: 260528 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0955. Min Range: -6.0955
Max Act: 5.8455. Min Act: -0.1700
Data Index: 2506632 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0955. Min Range: -6.0955
Max Act: 5.8768. Min Act: -0.1700
Data Index: 2918993 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0955. Min Range: -6.0955
Max Act: 5.8143. Min Act: -0.1700
Data Index: 7358994 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0955. Min Range: -6.0955
Max Act: 5.7518. Min Act: -0.1700
Data Index: 39124 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0955. Min Range: -6.0955
Max Act: 5.7830. Min Act: -0.1700
Data Index: 2273539 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0955. Min Range: -6.0955
Max Act: 5.7830. Min Act: -0.1700
Data Index: 3418693 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0955. Min Range: -6.0955
Max Act: 5.7518. Min Act: -0.1700
Data Index: 1432735 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0955. Min Range: -6.0955
Max Act: 5.7518. Min Act: -0.1700
Data Index: 4813786 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0955. Min Range: -6.0955
Max Act: 5.7205. Min Act: -0.1700
Data Index: 1259408 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0955. Min Range: -6.0955
Max Act: 5.7205. Min Act: -0.1700
Data Index: 7345380 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0955. Min Range: -6.0955
Max Act: 5.7205. Min Act: -0.1700
Data Index: 6794889 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0955. Min Range: -6.0955
Max Act: 5.7205. Min Act: -0.1700
Data Index: 2222421 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0955. Min Range: -6.0955
Max Act: 5.7205. Min Act: -0.1700
Data Index: 4163722 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0955. Min Range: -6.0955
Max Act: 5.6893. Min Act: -0.1700
Data Index: 673274 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0955. Min Range: -6.0955
Max Act: 5.6893. Min Act: -0.1700
Data Index: 5357041 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0955. Min Range: -6.0955
Max Act: 5.6893. Min Act: -0.1700
Data Index: 592462 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0955. Min Range: -6.0955
Max Act: 5.6893. Min Act: -0.1700
Data Index: 2012211 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19