Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3346 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3064. Min Range: -5.3064
Max Act: 5.3064. Min Act: -0.1700
Data Index: 1538746 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3064. Min Range: -5.3064
Max Act: 5.1189. Min Act: -0.1700
Data Index: 706722 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3064. Min Range: -5.3064
Max Act: 5.1189. Min Act: -0.1700
Data Index: 6194490 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3064. Min Range: -5.3064
Max Act: 5.1189. Min Act: -0.1700
Data Index: 2638383 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3064. Min Range: -5.3064
Max Act: 5.0564. Min Act: -0.1700
Data Index: 394255 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3064. Min Range: -5.3064
Max Act: 5.0564. Min Act: -0.1700
Data Index: 7251333 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3064. Min Range: -5.3064
Max Act: 5.0252. Min Act: -0.1700
Data Index: 2682929 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3064. Min Range: -5.3064
Max Act: 5.0252. Min Act: -0.1700
Data Index: 3225894 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3064. Min Range: -5.3064
Max Act: 5.0252. Min Act: -0.1700
Data Index: 79608 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3064. Min Range: -5.3064
Max Act: 4.9939. Min Act: -0.1700
Data Index: 6311717 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3064. Min Range: -5.3064
Max Act: 4.9939. Min Act: -0.1700
Data Index: 2348534 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3064. Min Range: -5.3064
Max Act: 4.9939. Min Act: -0.1700
Data Index: 2603945 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3064. Min Range: -5.3064
Max Act: 4.9939. Min Act: -0.1700
Data Index: 7139256 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3064. Min Range: -5.3064
Max Act: 4.9627. Min Act: -0.1700
Data Index: 6955146 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3064. Min Range: -5.3064
Max Act: 4.9627. Min Act: -0.1700
Data Index: 4773874 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3064. Min Range: -5.3064
Max Act: 4.9627. Min Act: -0.1700
Data Index: 7867887 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3064. Min Range: -5.3064
Max Act: 4.9627. Min Act: -0.1700
Data Index: 3091666 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3064. Min Range: -5.3064
Max Act: 4.9627. Min Act: -0.1700
Data Index: 4431904 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3064. Min Range: -5.3064
Max Act: 4.9314. Min Act: -0.1700
Data Index: 287874 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3064. Min Range: -5.3064
Max Act: 4.9627. Min Act: -0.1700
Data Index: 6543058 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19