Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4707 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3102. Min Range: -7.3102
Max Act: 7.3102. Min Act: -0.1700
Data Index: 3714687 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3102. Min Range: -7.3102
Max Act: 7.0602. Min Act: -0.1700
Data Index: 7807207 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.9665. Min Act: -0.1700
Data Index: 183995 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.9665. Min Act: -0.1700
Data Index: 4482711 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.8727. Min Act: -0.1700
Data Index: 8502154 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.9040. Min Act: -0.1700
Data Index: 223300 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.8727. Min Act: -0.1700
Data Index: 2055434 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.8415. Min Act: -0.1700
Data Index: 5010398 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.8102. Min Act: -0.1700
Data Index: 1917709 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.8102. Min Act: -0.1700
Data Index: 4341811 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.7790. Min Act: -0.1700
Data Index: 7685781 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.8415. Min Act: -0.1700
Data Index: 4046995 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.7790. Min Act: -0.1700
Data Index: 2258884 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.7790. Min Act: -0.1700
Data Index: 4750275 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.8102. Min Act: -0.1700
Data Index: 4101023 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.7790. Min Act: -0.1700
Data Index: 3384286 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.7477. Min Act: -0.1700
Data Index: 7330956 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.7477. Min Act: -0.1700
Data Index: 2852714 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.7165. Min Act: -0.1700
Data Index: 4228700 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3102. Min Range: -7.3102
Max Act: 6.6852. Min Act: -0.1700
Data Index: 1762746 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #19