Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3628 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3666. Min Range: -8.3666
Max Act: 8.3666. Min Act: -0.1700
Data Index: 3668817 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3666. Min Range: -8.3666
Max Act: 8.3666. Min Act: -0.1700
Data Index: 3108791 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3666. Min Range: -8.3666
Max Act: 8.1791. Min Act: -0.1700
Data Index: 2486744 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3666. Min Range: -8.3666
Max Act: 8.1479. Min Act: -0.1700
Data Index: 1683482 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3666. Min Range: -8.3666
Max Act: 8.0854. Min Act: -0.1700
Data Index: 5783620 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3666. Min Range: -8.3666
Max Act: 8.0854. Min Act: -0.1700
Data Index: 2111829 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3666. Min Range: -8.3666
Max Act: 8.0541. Min Act: -0.1700
Data Index: 256922 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3666. Min Range: -8.3666
Max Act: 8.0541. Min Act: -0.1700
Data Index: 974233 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3666. Min Range: -8.3666
Max Act: 8.0541. Min Act: -0.1700
Data Index: 8718176 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3666. Min Range: -8.3666
Max Act: 8.0541. Min Act: -0.1700
Data Index: 6349297 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3666. Min Range: -8.3666
Max Act: 7.9916. Min Act: -0.1700
Data Index: 5823206 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3666. Min Range: -8.3666
Max Act: 8.0229. Min Act: -0.1700
Data Index: 7744693 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3666. Min Range: -8.3666
Max Act: 7.9916. Min Act: -0.1700
Data Index: 2785276 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3666. Min Range: -8.3666
Max Act: 7.9604. Min Act: -0.1700
Data Index: 2970617 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3666. Min Range: -8.3666
Max Act: 7.9916. Min Act: -0.1700
Data Index: 7654234 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3666. Min Range: -8.3666
Max Act: 7.9916. Min Act: -0.1700
Data Index: 7654235 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3666. Min Range: -8.3666
Max Act: 7.9604. Min Act: -0.1700
Data Index: 8213969 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3666. Min Range: -8.3666
Max Act: 7.9604. Min Act: -0.1700
Data Index: 3204962 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3666. Min Range: -8.3666
Max Act: 7.8979. Min Act: -0.1700
Data Index: 4045950 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3666. Min Range: -8.3666
Max Act: 7.9291. Min Act: -0.1700
Data Index: 262452 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #19