Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1957 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2538. Min Range: -5.2538
Max Act: 5.2538. Min Act: -0.1700
Data Index: 6687604 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2538. Min Range: -5.2538
Max Act: 5.2226. Min Act: -0.1700
Data Index: 3772780 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2538. Min Range: -5.2538
Max Act: 5.1913. Min Act: -0.1700
Data Index: 5553325 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2538. Min Range: -5.2538
Max Act: 5.1601. Min Act: -0.1700
Data Index: 4304111 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2538. Min Range: -5.2538
Max Act: 5.0976. Min Act: -0.1700
Data Index: 2642263 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2538. Min Range: -5.2538
Max Act: 5.0976. Min Act: -0.1700
Data Index: 6442691 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2538. Min Range: -5.2538
Max Act: 5.0663. Min Act: -0.1700
Data Index: 2209557 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2538. Min Range: -5.2538
Max Act: 5.0663. Min Act: -0.1700
Data Index: 2808382 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2538. Min Range: -5.2538
Max Act: 5.0663. Min Act: -0.1700
Data Index: 1312918 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2538. Min Range: -5.2538
Max Act: 5.0663. Min Act: -0.1700
Data Index: 4398890 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2538. Min Range: -5.2538
Max Act: 5.0663. Min Act: -0.1700
Data Index: 4256092 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2538. Min Range: -5.2538
Max Act: 5.0351. Min Act: -0.1700
Data Index: 2797876 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2538. Min Range: -5.2538
Max Act: 5.0038. Min Act: -0.1700
Data Index: 3849982 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2538. Min Range: -5.2538
Max Act: 5.0038. Min Act: -0.1700
Data Index: 7632089 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2538. Min Range: -5.2538
Max Act: 5.0038. Min Act: -0.1700
Data Index: 3055585 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2538. Min Range: -5.2538
Max Act: 4.9413. Min Act: -0.1700
Data Index: 5926343 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2538. Min Range: -5.2538
Max Act: 4.9726. Min Act: -0.1700
Data Index: 4776876 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2538. Min Range: -5.2538
Max Act: 4.9413. Min Act: -0.1700
Data Index: 3324414 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2538. Min Range: -5.2538
Max Act: 5.0038. Min Act: -0.1700
Data Index: 5624639 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2538. Min Range: -5.2538
Max Act: 4.9726. Min Act: -0.1700
Data Index: 1814579 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19