Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3699 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6674. Min Range: -7.6674
Max Act: 7.6674. Min Act: -0.1700
Data Index: 8308239 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6674. Min Range: -7.6674
Max Act: 7.4486. Min Act: -0.1700
Data Index: 6774723 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6674. Min Range: -7.6674
Max Act: 7.3236. Min Act: -0.1700
Data Index: 2539360 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6674. Min Range: -7.6674
Max Act: 7.1986. Min Act: -0.1700
Data Index: 961957 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6674. Min Range: -7.6674
Max Act: 7.0736. Min Act: -0.1700
Data Index: 8774935 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6674. Min Range: -7.6674
Max Act: 6.9799. Min Act: -0.1700
Data Index: 6367048 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6674. Min Range: -7.6674
Max Act: 6.9486. Min Act: -0.1700
Data Index: 3480792 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6674. Min Range: -7.6674
Max Act: 6.9486. Min Act: -0.1700
Data Index: 4698634 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6674. Min Range: -7.6674
Max Act: 6.9174. Min Act: -0.1700
Data Index: 5794240 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6674. Min Range: -7.6674
Max Act: 6.9174. Min Act: -0.1700
Data Index: 4546856 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6674. Min Range: -7.6674
Max Act: 6.9174. Min Act: -0.1700
Data Index: 2892395 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6674. Min Range: -7.6674
Max Act: 6.8861. Min Act: -0.1700
Data Index: 7462086 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6674. Min Range: -7.6674
Max Act: 6.8549. Min Act: -0.1700
Data Index: 3262976 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6674. Min Range: -7.6674
Max Act: 6.8549. Min Act: -0.1700
Data Index: 4085727 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6674. Min Range: -7.6674
Max Act: 6.8549. Min Act: -0.1700
Data Index: 7715809 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6674. Min Range: -7.6674
Max Act: 6.8549. Min Act: -0.1700
Data Index: 3746518 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6674. Min Range: -7.6674
Max Act: 6.8549. Min Act: -0.1700
Data Index: 6240663 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6674. Min Range: -7.6674
Max Act: 6.8236. Min Act: -0.1700
Data Index: 5071079 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6674. Min Range: -7.6674
Max Act: 6.8236. Min Act: -0.1700
Data Index: 4201083 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6674. Min Range: -7.6674
Max Act: 6.7924. Min Act: -0.1700
Data Index: 1410586 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #19