Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 46 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2305. Min Range: -5.2305
Max Act: 5.2305. Min Act: -0.1700
Data Index: 294672 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2305. Min Range: -5.2305
Max Act: 5.1993. Min Act: -0.1700
Data Index: 1045094 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2305. Min Range: -5.2305
Max Act: 5.1680. Min Act: -0.1700
Data Index: 8628644 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2305. Min Range: -5.2305
Max Act: 5.1368. Min Act: -0.1700
Data Index: 3771767 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2305. Min Range: -5.2305
Max Act: 5.1680. Min Act: -0.1700
Data Index: 1366854 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2305. Min Range: -5.2305
Max Act: 5.1055. Min Act: -0.1700
Data Index: 6311797 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2305. Min Range: -5.2305
Max Act: 5.1368. Min Act: -0.1700
Data Index: 2245590 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2305. Min Range: -5.2305
Max Act: 5.1368. Min Act: -0.1700
Data Index: 7648575 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2305. Min Range: -5.2305
Max Act: 5.1055. Min Act: -0.1700
Data Index: 1429598 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2305. Min Range: -5.2305
Max Act: 5.0743. Min Act: -0.1700
Data Index: 5415092 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2305. Min Range: -5.2305
Max Act: 5.0430. Min Act: -0.1700
Data Index: 1961084 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2305. Min Range: -5.2305
Max Act: 5.0118. Min Act: -0.1700
Data Index: 2627332 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2305. Min Range: -5.2305
Max Act: 5.0118. Min Act: -0.1700
Data Index: 3864151 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2305. Min Range: -5.2305
Max Act: 5.0118. Min Act: -0.1700
Data Index: 822876 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2305. Min Range: -5.2305
Max Act: 4.9805. Min Act: -0.1700
Data Index: 5008618 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2305. Min Range: -5.2305
Max Act: 4.9805. Min Act: -0.1700
Data Index: 1758640 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2305. Min Range: -5.2305
Max Act: 4.9805. Min Act: -0.1700
Data Index: 8191315 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2305. Min Range: -5.2305
Max Act: 4.9805. Min Act: -0.1700
Data Index: 8410258 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2305. Min Range: -5.2305
Max Act: 4.9805. Min Act: -0.1700
Data Index: 7072622 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2305. Min Range: -5.2305
Max Act: 4.9805. Min Act: -0.1700
Data Index: 3075973 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19