Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2965 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.5215. Min Act: -0.1700
Data Index: 3359151 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.5215. Min Act: -0.1700
Data Index: 5849072 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.4902. Min Act: -0.1700
Data Index: 6063150 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.3965. Min Act: -0.1700
Data Index: 1503410 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.3652. Min Act: -0.1700
Data Index: 3523953 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.3652. Min Act: -0.1700
Data Index: 8110462 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.3027. Min Act: -0.1700
Data Index: 3714464 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.2714. Min Act: -0.1700
Data Index: 4066546 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.3027. Min Act: -0.1700
Data Index: 5240138 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.2714. Min Act: -0.1700
Data Index: 3359139 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.2402. Min Act: -0.1700
Data Index: 2434098 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.2714. Min Act: -0.1700
Data Index: 4855879 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.2402. Min Act: -0.1700
Data Index: 8155674 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.2402. Min Act: -0.1700
Data Index: 2434085 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.2402. Min Act: -0.1700
Data Index: 7480964 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.2089. Min Act: -0.1700
Data Index: 2434069 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.2089. Min Act: -0.1700
Data Index: 2434073 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.1777. Min Act: -0.1700
Data Index: 2434082 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.2089. Min Act: -0.1700
Data Index: 2434087 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5215. Min Range: -4.5215
Max Act: 4.2089. Min Act: -0.1700
Data Index: 2781317 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19