Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3654 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2577. Min Range: -5.2577
Max Act: 5.2577. Min Act: -0.1700
Data Index: 2040938 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2577. Min Range: -5.2577
Max Act: 5.1952. Min Act: -0.1700
Data Index: 748827 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2577. Min Range: -5.2577
Max Act: 5.1952. Min Act: -0.1700
Data Index: 2018324 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2577. Min Range: -5.2577
Max Act: 5.1639. Min Act: -0.1700
Data Index: 1255654 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2577. Min Range: -5.2577
Max Act: 5.1639. Min Act: -0.1700
Data Index: 7427180 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2577. Min Range: -5.2577
Max Act: 5.1327. Min Act: -0.1700
Data Index: 4496182 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2577. Min Range: -5.2577
Max Act: 5.1327. Min Act: -0.1700
Data Index: 2459331 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2577. Min Range: -5.2577
Max Act: 5.1327. Min Act: -0.1700
Data Index: 3043621 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2577. Min Range: -5.2577
Max Act: 5.1327. Min Act: -0.1698
Data Index: 7822429 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2577. Min Range: -5.2577
Max Act: 5.1014. Min Act: -0.1700
Data Index: 6295244 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2577. Min Range: -5.2577
Max Act: 5.1014. Min Act: -0.1700
Data Index: 8067468 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2577. Min Range: -5.2577
Max Act: 5.0702. Min Act: -0.1700
Data Index: 2775919 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2577. Min Range: -5.2577
Max Act: 5.1014. Min Act: -0.1700
Data Index: 3888598 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2577. Min Range: -5.2577
Max Act: 5.0702. Min Act: -0.1700
Data Index: 1891506 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2577. Min Range: -5.2577
Max Act: 5.0702. Min Act: -0.1700
Data Index: 7642291 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2577. Min Range: -5.2577
Max Act: 5.0702. Min Act: -0.1700
Data Index: 6674868 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2577. Min Range: -5.2577
Max Act: 5.0389. Min Act: -0.1700
Data Index: 4036625 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2577. Min Range: -5.2577
Max Act: 5.0389. Min Act: -0.1700
Data Index: 4064473 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2577. Min Range: -5.2577
Max Act: 5.0702. Min Act: -0.1700
Data Index: 3201911 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2577. Min Range: -5.2577
Max Act: 5.0389. Min Act: -0.1700
Data Index: 4658222 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19