Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3109 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8520. Min Range: -3.8520
Max Act: 3.8520. Min Act: -0.1700
Data Index: 3021681 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8520. Min Range: -3.8520
Max Act: 3.8520. Min Act: -0.1700
Data Index: 1423396 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8520. Min Range: -3.8520
Max Act: 3.8051. Min Act: -0.1700
Data Index: 5775932 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8520. Min Range: -3.8520
Max Act: 3.8051. Min Act: -0.1700
Data Index: 7304731 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8520. Min Range: -3.8520
Max Act: 3.7426. Min Act: -0.1700
Data Index: 533071 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8520. Min Range: -3.8520
Max Act: 3.7426. Min Act: -0.1700
Data Index: 7304732 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8520. Min Range: -3.8520
Max Act: 3.6644. Min Act: -0.1700
Data Index: 5311745 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8520. Min Range: -3.8520
Max Act: 3.6800. Min Act: -0.1700
Data Index: 4510609 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8520. Min Range: -3.8520
Max Act: 3.6331. Min Act: -0.1700
Data Index: 8561043 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8520. Min Range: -3.8520
Max Act: 3.6331. Min Act: -0.1700
Data Index: 2047365 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8520. Min Range: -3.8520
Max Act: 3.6174. Min Act: -0.1700
Data Index: 2894052 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8520. Min Range: -3.8520
Max Act: 3.6018. Min Act: -0.1700
Data Index: 5958324 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8520. Min Range: -3.8520
Max Act: 3.6174. Min Act: -0.1700
Data Index: 7304729 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8520. Min Range: -3.8520
Max Act: 3.5861. Min Act: -0.1700
Data Index: 4956185 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8520. Min Range: -3.8520
Max Act: 3.5861. Min Act: -0.1700
Data Index: 3505045 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8520. Min Range: -3.8520
Max Act: 3.6018. Min Act: -0.1700
Data Index: 1104346 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8520. Min Range: -3.8520
Max Act: 3.5861. Min Act: -0.1700
Data Index: 3023352 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8520. Min Range: -3.8520
Max Act: 3.5861. Min Act: -0.1700
Data Index: 2817279 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8520. Min Range: -3.8520
Max Act: 3.5705. Min Act: -0.1700
Data Index: 8145515 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8520. Min Range: -3.8520
Max Act: 3.5548. Min Act: -0.1700
Data Index: 7049705 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19