Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 811 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5721. Min Range: -5.5721
Max Act: 5.5721. Min Act: -0.1700
Data Index: 1107837 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5721. Min Range: -5.5721
Max Act: 5.5721. Min Act: -0.1700
Data Index: 2881431 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5721. Min Range: -5.5721
Max Act: 5.5096. Min Act: -0.1700
Data Index: 4798738 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5721. Min Range: -5.5721
Max Act: 5.4158. Min Act: -0.1700
Data Index: 5471401 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5721. Min Range: -5.5721
Max Act: 5.4158. Min Act: -0.1700
Data Index: 2307098 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5721. Min Range: -5.5721
Max Act: 5.4158. Min Act: -0.1700
Data Index: 4034606 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5721. Min Range: -5.5721
Max Act: 5.4158. Min Act: -0.1700
Data Index: 6927856 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5721. Min Range: -5.5721
Max Act: 5.3846. Min Act: -0.1700
Data Index: 4695193 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5721. Min Range: -5.5721
Max Act: 5.3846. Min Act: -0.1700
Data Index: 3875513 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5721. Min Range: -5.5721
Max Act: 5.4158. Min Act: -0.1700
Data Index: 4742653 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5721. Min Range: -5.5721
Max Act: 5.3846. Min Act: -0.1700
Data Index: 5909952 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5721. Min Range: -5.5721
Max Act: 5.3533. Min Act: -0.1700
Data Index: 4973593 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5721. Min Range: -5.5721
Max Act: 5.3221. Min Act: -0.1700
Data Index: 3232355 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5721. Min Range: -5.5721
Max Act: 5.3533. Min Act: -0.1700
Data Index: 247911 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5721. Min Range: -5.5721
Max Act: 5.3221. Min Act: -0.1700
Data Index: 7735688 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5721. Min Range: -5.5721
Max Act: 5.3221. Min Act: -0.1700
Data Index: 2770467 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5721. Min Range: -5.5721
Max Act: 5.2908. Min Act: -0.1700
Data Index: 3307155 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5721. Min Range: -5.5721
Max Act: 5.3221. Min Act: -0.1700
Data Index: 2175426 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5721. Min Range: -5.5721
Max Act: 5.3221. Min Act: -0.1700
Data Index: 1462731 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5721. Min Range: -5.5721
Max Act: 5.2908. Min Act: -0.1680
Data Index: 7173396 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #19