Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2643 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.8105. Min Range: -1.8105
Max Act: 1.8105. Min Act: -0.1700
Data Index: 5387776 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8105. Min Range: -1.8105
Max Act: 1.7243. Min Act: -0.1700
Data Index: 4736305 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8105. Min Range: -1.8105
Max Act: 1.7243. Min Act: -0.1700
Data Index: 6228279 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8105. Min Range: -1.8105
Max Act: 1.7243. Min Act: -0.1700
Data Index: 3539778 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8105. Min Range: -1.8105
Max Act: 1.7243. Min Act: -0.1700
Data Index: 7827038 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8105. Min Range: -1.8105
Max Act: 1.6896. Min Act: -0.1700
Data Index: 7029614 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8105. Min Range: -1.8105
Max Act: 1.6896. Min Act: -0.1700
Data Index: 8033610 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8105. Min Range: -1.8105
Max Act: 1.6896. Min Act: -0.1700
Data Index: 3977164 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8105. Min Range: -1.8105
Max Act: 1.6896. Min Act: -0.1700
Data Index: 7989922 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8105. Min Range: -1.8105
Max Act: 1.6375. Min Act: -0.1700
Data Index: 5475850 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8105. Min Range: -1.8105
Max Act: 1.6375. Min Act: -0.1700
Data Index: 8172621 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8105. Min Range: -1.8105
Max Act: 1.6375. Min Act: -0.1700
Data Index: 2856437 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8105. Min Range: -1.8105
Max Act: 1.6375. Min Act: -0.1697
Data Index: 346131 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8105. Min Range: -1.8105
Max Act: 1.6375. Min Act: -0.1699
Data Index: 4778203 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8105. Min Range: -1.8105
Max Act: 1.5851. Min Act: -0.1698
Data Index: 610401 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8105. Min Range: -1.8105
Max Act: 1.5501. Min Act: -0.1700
Data Index: 4680026 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8105. Min Range: -1.8105
Max Act: 1.5501. Min Act: -0.1688
Data Index: 222625 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8105. Min Range: -1.8105
Max Act: 1.5326. Min Act: -0.1700
Data Index: 1735666 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8105. Min Range: -1.8105
Max Act: 1.5326. Min Act: -0.1700
Data Index: 6495391 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8105. Min Range: -1.8105
Max Act: 1.4975. Min Act: -0.1700
Data Index: 4958035 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19