Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3628 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6257. Min Range: -4.6257
Max Act: 4.6257. Min Act: -0.1700
Data Index: 7738908 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6257. Min Range: -4.6257
Max Act: 4.5007. Min Act: -0.1700
Data Index: 7840430 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6257. Min Range: -4.6257
Max Act: 4.4695. Min Act: -0.1700
Data Index: 1484472 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6257. Min Range: -4.6257
Max Act: 4.4695. Min Act: -0.1700
Data Index: 5823581 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6257. Min Range: -4.6257
Max Act: 4.4070. Min Act: -0.1700
Data Index: 5911266 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6257. Min Range: -4.6257
Max Act: 4.4070. Min Act: -0.1700
Data Index: 7512938 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6257. Min Range: -4.6257
Max Act: 4.3757. Min Act: -0.1700
Data Index: 5232060 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6257. Min Range: -4.6257
Max Act: 4.3757. Min Act: -0.1700
Data Index: 3435133 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6257. Min Range: -4.6257
Max Act: 4.3445. Min Act: -0.1700
Data Index: 1173332 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6257. Min Range: -4.6257
Max Act: 4.3445. Min Act: -0.1700
Data Index: 7550529 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6257. Min Range: -4.6257
Max Act: 4.3445. Min Act: -0.1700
Data Index: 2000497 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6257. Min Range: -4.6257
Max Act: 4.3445. Min Act: -0.1700
Data Index: 3303323 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6257. Min Range: -4.6257
Max Act: 4.3445. Min Act: -0.1700
Data Index: 2615734 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6257. Min Range: -4.6257
Max Act: 4.3132. Min Act: -0.1700
Data Index: 983750 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6257. Min Range: -4.6257
Max Act: 4.3132. Min Act: -0.1700
Data Index: 3944158 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6257. Min Range: -4.6257
Max Act: 4.3132. Min Act: -0.1700
Data Index: 5678643 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6257. Min Range: -4.6257
Max Act: 4.2820. Min Act: -0.1700
Data Index: 1320423 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6257. Min Range: -4.6257
Max Act: 4.2820. Min Act: -0.1700
Data Index: 1280172 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6257. Min Range: -4.6257
Max Act: 4.2820. Min Act: -0.1700
Data Index: 2493376 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6257. Min Range: -4.6257
Max Act: 4.2820. Min Act: -0.1700
Data Index: 8485756 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #19