Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2918 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1952. Min Range: -6.1952
Max Act: 6.1952. Min Act: -0.1700
Data Index: 6903853 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1952. Min Range: -6.1952
Max Act: 5.9452. Min Act: -0.1700
Data Index: 2241003 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1952. Min Range: -6.1952
Max Act: 5.7264. Min Act: -0.1700
Data Index: 8513686 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1952. Min Range: -6.1952
Max Act: 5.7264. Min Act: -0.1700
Data Index: 4936433 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1952. Min Range: -6.1952
Max Act: 5.7264. Min Act: -0.1700
Data Index: 4936432 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1952. Min Range: -6.1952
Max Act: 5.6952. Min Act: -0.1700
Data Index: 1922865 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1952. Min Range: -6.1952
Max Act: 5.6327. Min Act: -0.1700
Data Index: 812680 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1952. Min Range: -6.1952
Max Act: 5.6327. Min Act: -0.1700
Data Index: 7392559 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1952. Min Range: -6.1952
Max Act: 5.5702. Min Act: -0.1700
Data Index: 1739309 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1952. Min Range: -6.1952
Max Act: 5.6014. Min Act: -0.1700
Data Index: 8603861 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1952. Min Range: -6.1952
Max Act: 5.6014. Min Act: -0.1700
Data Index: 8494524 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1952. Min Range: -6.1952
Max Act: 5.6014. Min Act: -0.1700
Data Index: 46590 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1952. Min Range: -6.1952
Max Act: 5.5389. Min Act: -0.1700
Data Index: 1074219 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1952. Min Range: -6.1952
Max Act: 5.5702. Min Act: -0.1700
Data Index: 8217987 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1952. Min Range: -6.1952
Max Act: 5.5389. Min Act: -0.1700
Data Index: 1928042 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1952. Min Range: -6.1952
Max Act: 5.5389. Min Act: -0.1700
Data Index: 508586 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1952. Min Range: -6.1952
Max Act: 5.5389. Min Act: -0.1700
Data Index: 8297053 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1952. Min Range: -6.1952
Max Act: 5.5702. Min Act: -0.1700
Data Index: 7513691 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1952. Min Range: -6.1952
Max Act: 5.5389. Min Act: -0.1700
Data Index: 8696620 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1952. Min Range: -6.1952
Max Act: 5.5389. Min Act: -0.1700
Data Index: 3861277 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19