Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3717 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6765. Min Range: -7.6765
Max Act: 7.6765. Min Act: -0.1700
Data Index: 81846 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6765. Min Range: -7.6765
Max Act: 7.3640. Min Act: -0.1700
Data Index: 3253585 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6765. Min Range: -7.6765
Max Act: 7.3015. Min Act: -0.1700
Data Index: 138644 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6765. Min Range: -7.6765
Max Act: 7.3015. Min Act: -0.1700
Data Index: 5693026 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6765. Min Range: -7.6765
Max Act: 7.2702. Min Act: -0.1700
Data Index: 4791152 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6765. Min Range: -7.6765
Max Act: 7.2390. Min Act: -0.1700
Data Index: 3745800 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6765. Min Range: -7.6765
Max Act: 7.1765. Min Act: -0.1700
Data Index: 93783 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6765. Min Range: -7.6765
Max Act: 7.1765. Min Act: -0.1700
Data Index: 120957 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6765. Min Range: -7.6765
Max Act: 7.1452. Min Act: -0.1700
Data Index: 4024093 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6765. Min Range: -7.6765
Max Act: 7.1452. Min Act: -0.1700
Data Index: 3266057 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6765. Min Range: -7.6765
Max Act: 7.1452. Min Act: -0.1700
Data Index: 7765675 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6765. Min Range: -7.6765
Max Act: 7.1140. Min Act: -0.1700
Data Index: 4335362 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6765. Min Range: -7.6765
Max Act: 7.0827. Min Act: -0.1700
Data Index: 3205027 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6765. Min Range: -7.6765
Max Act: 7.0202. Min Act: -0.1700
Data Index: 4259495 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6765. Min Range: -7.6765
Max Act: 7.0202. Min Act: -0.1700
Data Index: 2351782 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6765. Min Range: -7.6765
Max Act: 6.9890. Min Act: -0.1700
Data Index: 745175 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6765. Min Range: -7.6765
Max Act: 6.9577. Min Act: -0.1700
Data Index: 4844086 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6765. Min Range: -7.6765
Max Act: 6.9265. Min Act: -0.1700
Data Index: 5211289 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6765. Min Range: -7.6765
Max Act: 6.9265. Min Act: -0.1700
Data Index: 605353 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6765. Min Range: -7.6765
Max Act: 6.9265. Min Act: -0.1700
Data Index: 4957859 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19