Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2613 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7461. Min Range: -5.7461
Max Act: 5.7461. Min Act: -0.1700
Data Index: 2824674 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7461. Min Range: -5.7461
Max Act: 5.5274. Min Act: -0.1700
Data Index: 8652698 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7461. Min Range: -5.7461
Max Act: 5.4961. Min Act: -0.1700
Data Index: 8652704 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7461. Min Range: -5.7461
Max Act: 5.3399. Min Act: -0.1700
Data Index: 2988409 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7461. Min Range: -5.7461
Max Act: 5.3711. Min Act: -0.1700
Data Index: 8786267 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7461. Min Range: -5.7461
Max Act: 5.4024. Min Act: -0.1700
Data Index: 3211000 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7461. Min Range: -5.7461
Max Act: 5.2461. Min Act: -0.1700
Data Index: 1829729 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7461. Min Range: -5.7461
Max Act: 5.2461. Min Act: -0.1700
Data Index: 5727970 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7461. Min Range: -5.7461
Max Act: 5.2461. Min Act: -0.1700
Data Index: 7073325 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7461. Min Range: -5.7461
Max Act: 5.2149. Min Act: -0.1700
Data Index: 8775797 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7461. Min Range: -5.7461
Max Act: 5.1836. Min Act: -0.1700
Data Index: 1594096 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7461. Min Range: -5.7461
Max Act: 5.1836. Min Act: -0.1700
Data Index: 1952208 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7461. Min Range: -5.7461
Max Act: 5.1836. Min Act: -0.1700
Data Index: 7051656 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7461. Min Range: -5.7461
Max Act: 5.1836. Min Act: -0.1700
Data Index: 1679626 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7461. Min Range: -5.7461
Max Act: 5.1211. Min Act: -0.1700
Data Index: 5435183 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7461. Min Range: -5.7461
Max Act: 5.1524. Min Act: -0.1700
Data Index: 8247424 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7461. Min Range: -5.7461
Max Act: 5.1211. Min Act: -0.1700
Data Index: 5556410 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7461. Min Range: -5.7461
Max Act: 5.1524. Min Act: -0.1700
Data Index: 6139146 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7461. Min Range: -5.7461
Max Act: 5.1524. Min Act: -0.1700
Data Index: 8407077 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7461. Min Range: -5.7461
Max Act: 5.1524. Min Act: -0.1700
Data Index: 7208824 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19