Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2214 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6622. Min Range: -7.6622
Max Act: 7.6622. Min Act: -0.1700
Data Index: 6175532 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6622. Min Range: -7.6622
Max Act: 7.5997. Min Act: -0.1700
Data Index: 1968739 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6622. Min Range: -7.6622
Max Act: 7.5059. Min Act: -0.1700
Data Index: 8216707 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6622. Min Range: -7.6622
Max Act: 7.4747. Min Act: -0.1700
Data Index: 1006024 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6622. Min Range: -7.6622
Max Act: 7.3497. Min Act: -0.1700
Data Index: 2230610 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6622. Min Range: -7.6622
Max Act: 7.3497. Min Act: -0.1700
Data Index: 553995 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6622. Min Range: -7.6622
Max Act: 7.2872. Min Act: -0.1700
Data Index: 4475092 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6622. Min Range: -7.6622
Max Act: 7.2559. Min Act: -0.1700
Data Index: 5412557 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6622. Min Range: -7.6622
Max Act: 7.2559. Min Act: -0.1700
Data Index: 553967 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6622. Min Range: -7.6622
Max Act: 7.1622. Min Act: -0.1700
Data Index: 7797261 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6622. Min Range: -7.6622
Max Act: 7.1622. Min Act: -0.1700
Data Index: 7540998 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6622. Min Range: -7.6622
Max Act: 7.1622. Min Act: -0.1700
Data Index: 2796062 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6622. Min Range: -7.6622
Max Act: 7.0684. Min Act: -0.1700
Data Index: 554000 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6622. Min Range: -7.6622
Max Act: 7.0372. Min Act: -0.1700
Data Index: 4445226 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6622. Min Range: -7.6622
Max Act: 7.0059. Min Act: -0.1700
Data Index: 3465097 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6622. Min Range: -7.6622
Max Act: 7.0372. Min Act: -0.1700
Data Index: 8149716 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6622. Min Range: -7.6622
Max Act: 7.0059. Min Act: -0.1700
Data Index: 2696768 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6622. Min Range: -7.6622
Max Act: 7.0059. Min Act: -0.1700
Data Index: 1891744 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6622. Min Range: -7.6622
Max Act: 7.0059. Min Act: -0.1700
Data Index: 7355980 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6622. Min Range: -7.6622
Max Act: 6.9747. Min Act: -0.1700
Data Index: 4038658 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19