Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6333 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9739. Min Range: -4.9739
Max Act: 4.9739. Min Act: -0.1700
Data Index: 8750154 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9739. Min Range: -4.9739
Max Act: 4.4426. Min Act: -0.1700
Data Index: 7752836 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9739. Min Range: -4.9739
Max Act: 4.2864. Min Act: -0.1700
Data Index: 2317491 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9739. Min Range: -4.9739
Max Act: 4.2551. Min Act: -0.1700
Data Index: 643211 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9739. Min Range: -4.9739
Max Act: 4.1301. Min Act: -0.1700
Data Index: 4466969 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9739. Min Range: -4.9739
Max Act: 4.0989. Min Act: -0.1700
Data Index: 7883472 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9739. Min Range: -4.9739
Max Act: 4.0676. Min Act: -0.1700
Data Index: 3147161 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9739. Min Range: -4.9739
Max Act: 4.0676. Min Act: -0.1700
Data Index: 3135219 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9739. Min Range: -4.9739
Max Act: 4.0676. Min Act: -0.1700
Data Index: 8763643 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9739. Min Range: -4.9739
Max Act: 4.0676. Min Act: -0.1700
Data Index: 1677264 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9739. Min Range: -4.9739
Max Act: 4.0363. Min Act: -0.1700
Data Index: 4481334 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9739. Min Range: -4.9739
Max Act: 4.0363. Min Act: -0.1700
Data Index: 1149365 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9739. Min Range: -4.9739
Max Act: 4.0363. Min Act: -0.1700
Data Index: 8632858 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9739. Min Range: -4.9739
Max Act: 4.0363. Min Act: -0.1700
Data Index: 6938840 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9739. Min Range: -4.9739
Max Act: 4.0051. Min Act: -0.1700
Data Index: 2547489 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9739. Min Range: -4.9739
Max Act: 4.0051. Min Act: -0.1700
Data Index: 6101130 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9739. Min Range: -4.9739
Max Act: 4.0051. Min Act: -0.1700
Data Index: 4092004 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9739. Min Range: -4.9739
Max Act: 3.9738. Min Act: -0.1700
Data Index: 7374814 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9739. Min Range: -4.9739
Max Act: 4.0051. Min Act: -0.1700
Data Index: 7739483 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9739. Min Range: -4.9739
Max Act: 3.9738. Min Act: -0.1700
Data Index: 240160 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #19