Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5311 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0621. Min Range: -5.0621
Max Act: 5.0621. Min Act: -0.1700
Data Index: 7702699 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0621. Min Range: -5.0621
Max Act: 5.0309. Min Act: -0.1700
Data Index: 6946229 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0621. Min Range: -5.0621
Max Act: 5.0621. Min Act: -0.1700
Data Index: 8376856 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0621. Min Range: -5.0621
Max Act: 5.0309. Min Act: -0.1700
Data Index: 35964 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0621. Min Range: -5.0621
Max Act: 5.0309. Min Act: -0.1700
Data Index: 2172405 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0621. Min Range: -5.0621
Max Act: 4.9996. Min Act: -0.1700
Data Index: 5366605 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0621. Min Range: -5.0621
Max Act: 4.9996. Min Act: -0.1700
Data Index: 2713085 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0621. Min Range: -5.0621
Max Act: 4.9996. Min Act: -0.1700
Data Index: 3221430 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0621. Min Range: -5.0621
Max Act: 4.9996. Min Act: -0.1700
Data Index: 291325 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0621. Min Range: -5.0621
Max Act: 4.9996. Min Act: -0.1700
Data Index: 514759 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0621. Min Range: -5.0621
Max Act: 4.9684. Min Act: -0.1700
Data Index: 1287150 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0621. Min Range: -5.0621
Max Act: 4.9684. Min Act: -0.1700
Data Index: 2582677 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0621. Min Range: -5.0621
Max Act: 4.9684. Min Act: -0.1700
Data Index: 5553007 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0621. Min Range: -5.0621
Max Act: 4.9684. Min Act: -0.1700
Data Index: 4542678 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0621. Min Range: -5.0621
Max Act: 4.9684. Min Act: -0.1700
Data Index: 1545179 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0621. Min Range: -5.0621
Max Act: 4.9684. Min Act: -0.1700
Data Index: 3023990 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0621. Min Range: -5.0621
Max Act: 4.9371. Min Act: -0.1700
Data Index: 1097388 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0621. Min Range: -5.0621
Max Act: 4.9371. Min Act: -0.1700
Data Index: 5956101 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0621. Min Range: -5.0621
Max Act: 4.9371. Min Act: -0.1700
Data Index: 4353799 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0621. Min Range: -5.0621
Max Act: 4.9371. Min Act: -0.1700
Data Index: 6015707 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #19