Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5232 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6447. Min Range: -4.6447
Max Act: 4.6447. Min Act: -0.1700
Data Index: 7755470 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6447. Min Range: -4.6447
Max Act: 4.5822. Min Act: -0.1700
Data Index: 562808 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6447. Min Range: -4.6447
Max Act: 4.5822. Min Act: -0.1700
Data Index: 910245 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6447. Min Range: -4.6447
Max Act: 4.5510. Min Act: -0.1700
Data Index: 4498461 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6447. Min Range: -4.6447
Max Act: 4.5510. Min Act: -0.1699
Data Index: 5404698 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6447. Min Range: -4.6447
Max Act: 4.5197. Min Act: -0.1700
Data Index: 1889085 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6447. Min Range: -4.6447
Max Act: 4.4885. Min Act: -0.1700
Data Index: 8015474 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6447. Min Range: -4.6447
Max Act: 4.4885. Min Act: -0.1700
Data Index: 6002922 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6447. Min Range: -4.6447
Max Act: 4.4572. Min Act: -0.1700
Data Index: 7365948 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6447. Min Range: -4.6447
Max Act: 4.4572. Min Act: -0.1697
Data Index: 5087468 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6447. Min Range: -4.6447
Max Act: 4.4572. Min Act: -0.1700
Data Index: 5061837 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6447. Min Range: -4.6447
Max Act: 4.4885. Min Act: -0.1700
Data Index: 219424 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6447. Min Range: -4.6447
Max Act: 4.4572. Min Act: -0.1700
Data Index: 2529367 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6447. Min Range: -4.6447
Max Act: 4.4572. Min Act: -0.1700
Data Index: 8271005 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6447. Min Range: -4.6447
Max Act: 4.4260. Min Act: -0.1700
Data Index: 2811741 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6447. Min Range: -4.6447
Max Act: 4.4260. Min Act: -0.1700
Data Index: 1729798 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6447. Min Range: -4.6447
Max Act: 4.4260. Min Act: -0.1700
Data Index: 3472225 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6447. Min Range: -4.6447
Max Act: 4.4260. Min Act: -0.1700
Data Index: 4593692 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6447. Min Range: -4.6447
Max Act: 4.4260. Min Act: -0.1700
Data Index: 3718228 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6447. Min Range: -4.6447
Max Act: 4.4260. Min Act: -0.1700
Data Index: 6451451 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19