Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2914 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0463. Min Range: -9.0463
Max Act: 9.0463. Min Act: -0.1700
Data Index: 5750548 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0463. Min Range: -9.0463
Max Act: 8.2338. Min Act: -0.1700
Data Index: 1031142 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0463. Min Range: -9.0463
Max Act: 8.1713. Min Act: -0.1700
Data Index: 4893091 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0463. Min Range: -9.0463
Max Act: 8.0463. Min Act: -0.1700
Data Index: 5067121 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0463. Min Range: -9.0463
Max Act: 8.0463. Min Act: -0.1700
Data Index: 8395507 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0463. Min Range: -9.0463
Max Act: 7.9838. Min Act: -0.1700
Data Index: 8348080 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0463. Min Range: -9.0463
Max Act: 7.9838. Min Act: -0.1700
Data Index: 5367562 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0463. Min Range: -9.0463
Max Act: 7.9838. Min Act: -0.1700
Data Index: 8052213 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0463. Min Range: -9.0463
Max Act: 7.8588. Min Act: -0.1700
Data Index: 8111552 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0463. Min Range: -9.0463
Max Act: 7.8588. Min Act: -0.1700
Data Index: 3639434 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0463. Min Range: -9.0463
Max Act: 7.8588. Min Act: -0.1700
Data Index: 1323619 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0463. Min Range: -9.0463
Max Act: 7.7963. Min Act: -0.1700
Data Index: 2350843 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0463. Min Range: -9.0463
Max Act: 7.7963. Min Act: -0.1700
Data Index: 7082403 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0463. Min Range: -9.0463
Max Act: 7.7963. Min Act: -0.1700
Data Index: 4088629 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0463. Min Range: -9.0463
Max Act: 7.7963. Min Act: -0.1700
Data Index: 6925840 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0463. Min Range: -9.0463
Max Act: 7.7963. Min Act: -0.1700
Data Index: 5309091 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0463. Min Range: -9.0463
Max Act: 7.7338. Min Act: -0.1700
Data Index: 3709996 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0463. Min Range: -9.0463
Max Act: 7.7338. Min Act: -0.1700
Data Index: 567680 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0463. Min Range: -9.0463
Max Act: 7.7338. Min Act: -0.1700
Data Index: 319034 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0463. Min Range: -9.0463
Max Act: 7.7338. Min Act: -0.1700
Data Index: 7051686 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #19