Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5294 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7297. Min Range: -6.7297
Max Act: 6.7297. Min Act: -0.1700
Data Index: 5402822 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7297. Min Range: -6.7297
Max Act: 6.4172. Min Act: -0.1700
Data Index: 1125784 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7297. Min Range: -6.7297
Max Act: 6.3547. Min Act: -0.1700
Data Index: 2765836 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7297. Min Range: -6.7297
Max Act: 6.2610. Min Act: -0.1700
Data Index: 3702235 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7297. Min Range: -6.7297
Max Act: 6.1672. Min Act: -0.1700
Data Index: 4486368 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7297. Min Range: -6.7297
Max Act: 6.1047. Min Act: -0.1700
Data Index: 4209899 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7297. Min Range: -6.7297
Max Act: 6.1360. Min Act: -0.1700
Data Index: 5175306 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7297. Min Range: -6.7297
Max Act: 6.0735. Min Act: -0.1700
Data Index: 3782318 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7297. Min Range: -6.7297
Max Act: 6.0422. Min Act: -0.1700
Data Index: 4758058 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7297. Min Range: -6.7297
Max Act: 6.0422. Min Act: -0.1700
Data Index: 1078812 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7297. Min Range: -6.7297
Max Act: 6.0422. Min Act: -0.1700
Data Index: 1942819 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7297. Min Range: -6.7297
Max Act: 6.0110. Min Act: -0.1700
Data Index: 5690748 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7297. Min Range: -6.7297
Max Act: 5.9797. Min Act: -0.1700
Data Index: 2476352 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7297. Min Range: -6.7297
Max Act: 5.9797. Min Act: -0.1700
Data Index: 4433581 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7297. Min Range: -6.7297
Max Act: 5.9485. Min Act: -0.1700
Data Index: 4720687 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7297. Min Range: -6.7297
Max Act: 5.9485. Min Act: -0.1700
Data Index: 8516306 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7297. Min Range: -6.7297
Max Act: 5.9172. Min Act: -0.1700
Data Index: 1942821 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7297. Min Range: -6.7297
Max Act: 5.9172. Min Act: -0.1700
Data Index: 123464 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7297. Min Range: -6.7297
Max Act: 5.9172. Min Act: -0.1700
Data Index: 8734389 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7297. Min Range: -6.7297
Max Act: 5.9172. Min Act: -0.1700
Data Index: 6277703 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #19