Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2431 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6389. Min Range: -6.6389
Max Act: 6.6389. Min Act: -0.1700
Data Index: 4023594 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6389. Min Range: -6.6389
Max Act: 6.0452. Min Act: -0.1700
Data Index: 6454722 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6389. Min Range: -6.6389
Max Act: 5.9202. Min Act: -0.1700
Data Index: 6302780 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6389. Min Range: -6.6389
Max Act: 5.9514. Min Act: -0.1700
Data Index: 4082348 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6389. Min Range: -6.6389
Max Act: 5.8577. Min Act: -0.1700
Data Index: 4446278 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6389. Min Range: -6.6389
Max Act: 5.8889. Min Act: -0.1700
Data Index: 5217565 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6389. Min Range: -6.6389
Max Act: 5.8577. Min Act: -0.1700
Data Index: 2310602 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6389. Min Range: -6.6389
Max Act: 5.8264. Min Act: -0.1700
Data Index: 8035069 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6389. Min Range: -6.6389
Max Act: 5.8264. Min Act: -0.1700
Data Index: 6017597 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6389. Min Range: -6.6389
Max Act: 5.7952. Min Act: -0.1700
Data Index: 642444 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6389. Min Range: -6.6389
Max Act: 5.7639. Min Act: -0.1700
Data Index: 8077667 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6389. Min Range: -6.6389
Max Act: 5.7327. Min Act: -0.1700
Data Index: 5477495 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6389. Min Range: -6.6389
Max Act: 5.7327. Min Act: -0.1700
Data Index: 8762859 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6389. Min Range: -6.6389
Max Act: 5.7327. Min Act: -0.1700
Data Index: 1538124 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6389. Min Range: -6.6389
Max Act: 5.7014. Min Act: -0.1700
Data Index: 3731023 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6389. Min Range: -6.6389
Max Act: 5.7014. Min Act: -0.1700
Data Index: 685910 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6389. Min Range: -6.6389
Max Act: 5.7327. Min Act: -0.1700
Data Index: 4509082 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6389. Min Range: -6.6389
Max Act: 5.6702. Min Act: -0.1700
Data Index: 4557553 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6389. Min Range: -6.6389
Max Act: 5.6389. Min Act: -0.1700
Data Index: 5496682 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6389. Min Range: -6.6389
Max Act: 5.6702. Min Act: -0.1700
Data Index: 7537354 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19