Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2912 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7024. Min Range: -4.7024
Max Act: 4.7024. Min Act: -0.1700
Data Index: 6803596 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7024. Min Range: -4.7024
Max Act: 4.4836. Min Act: -0.1700
Data Index: 4723273 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7024. Min Range: -4.7024
Max Act: 4.4836. Min Act: -0.1700
Data Index: 727855 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7024. Min Range: -4.7024
Max Act: 4.4211. Min Act: -0.1700
Data Index: 763709 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7024. Min Range: -4.7024
Max Act: 4.3899. Min Act: -0.1700
Data Index: 4576383 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7024. Min Range: -4.7024
Max Act: 4.3899. Min Act: -0.1700
Data Index: 221389 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7024. Min Range: -4.7024
Max Act: 4.3899. Min Act: -0.1700
Data Index: 1840056 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7024. Min Range: -4.7024
Max Act: 4.3586. Min Act: -0.1700
Data Index: 3942254 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7024. Min Range: -4.7024
Max Act: 4.3586. Min Act: -0.1700
Data Index: 1294577 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7024. Min Range: -4.7024
Max Act: 4.3586. Min Act: -0.1700
Data Index: 7859470 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7024. Min Range: -4.7024
Max Act: 4.3586. Min Act: -0.1700
Data Index: 7576807 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7024. Min Range: -4.7024
Max Act: 4.3586. Min Act: -0.1700
Data Index: 3942264 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7024. Min Range: -4.7024
Max Act: 4.3274. Min Act: -0.1700
Data Index: 8766399 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7024. Min Range: -4.7024
Max Act: 4.3274. Min Act: -0.1700
Data Index: 6306934 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7024. Min Range: -4.7024
Max Act: 4.2961. Min Act: -0.1700
Data Index: 1263600 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7024. Min Range: -4.7024
Max Act: 4.2961. Min Act: -0.1700
Data Index: 971138 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7024. Min Range: -4.7024
Max Act: 4.2961. Min Act: -0.1700
Data Index: 376637 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7024. Min Range: -4.7024
Max Act: 4.2649. Min Act: -0.1700
Data Index: 4040095 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7024. Min Range: -4.7024
Max Act: 4.2649. Min Act: -0.1700
Data Index: 7407510 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7024. Min Range: -4.7024
Max Act: 4.2024. Min Act: -0.1700
Data Index: 6823640 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #19