Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3147 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1762. Min Range: -8.1762
Max Act: 8.1762. Min Act: -0.1700
Data Index: 5670018 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1762. Min Range: -8.1762
Max Act: 7.4887. Min Act: -0.1700
Data Index: 2399182 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1762. Min Range: -8.1762
Max Act: 7.3950. Min Act: -0.1700
Data Index: 3609624 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1762. Min Range: -8.1762
Max Act: 7.3637. Min Act: -0.1700
Data Index: 3851998 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1762. Min Range: -8.1762
Max Act: 7.2700. Min Act: -0.1700
Data Index: 4247646 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1762. Min Range: -8.1762
Max Act: 7.2387. Min Act: -0.1700
Data Index: 7545025 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1762. Min Range: -8.1762
Max Act: 7.1450. Min Act: -0.1700
Data Index: 4967747 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1762. Min Range: -8.1762
Max Act: 7.1762. Min Act: -0.1700
Data Index: 7746032 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1762. Min Range: -8.1762
Max Act: 7.1450. Min Act: -0.1700
Data Index: 5505616 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1762. Min Range: -8.1762
Max Act: 7.0825. Min Act: -0.1700
Data Index: 138288 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1762. Min Range: -8.1762
Max Act: 7.0200. Min Act: -0.1700
Data Index: 4295021 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1762. Min Range: -8.1762
Max Act: 6.9887. Min Act: -0.1700
Data Index: 1936128 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1762. Min Range: -8.1762
Max Act: 6.9887. Min Act: -0.1700
Data Index: 1535209 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1762. Min Range: -8.1762
Max Act: 6.9887. Min Act: -0.1700
Data Index: 6822703 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1762. Min Range: -8.1762
Max Act: 6.9262. Min Act: -0.1700
Data Index: 8066923 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1762. Min Range: -8.1762
Max Act: 6.9887. Min Act: -0.1700
Data Index: 2886774 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1762. Min Range: -8.1762
Max Act: 6.9262. Min Act: -0.1700
Data Index: 856345 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1762. Min Range: -8.1762
Max Act: 6.9575. Min Act: -0.1700
Data Index: 2176213 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1762. Min Range: -8.1762
Max Act: 6.9262. Min Act: -0.1700
Data Index: 7353764 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1762. Min Range: -8.1762
Max Act: 6.8950. Min Act: -0.1700
Data Index: 304344 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19