Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 7 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9512. Min Range: -4.9512
Max Act: 4.9512. Min Act: -0.1700
Data Index: 8157848 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9512. Min Range: -4.9512
Max Act: 4.9200. Min Act: -0.1700
Data Index: 1289189 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9512. Min Range: -4.9512
Max Act: 4.9200. Min Act: -0.1700
Data Index: 7964547 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9512. Min Range: -4.9512
Max Act: 4.8887. Min Act: -0.1700
Data Index: 886576 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9512. Min Range: -4.9512
Max Act: 4.8575. Min Act: -0.1700
Data Index: 8191625 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9512. Min Range: -4.9512
Max Act: 4.8262. Min Act: -0.1700
Data Index: 6720290 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9512. Min Range: -4.9512
Max Act: 4.8262. Min Act: -0.1700
Data Index: 3059012 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9512. Min Range: -4.9512
Max Act: 4.7637. Min Act: -0.1700
Data Index: 7729282 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9512. Min Range: -4.9512
Max Act: 4.7637. Min Act: -0.1700
Data Index: 6538468 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9512. Min Range: -4.9512
Max Act: 4.7950. Min Act: -0.1700
Data Index: 1121901 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9512. Min Range: -4.9512
Max Act: 4.7012. Min Act: -0.1700
Data Index: 1033927 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9512. Min Range: -4.9512
Max Act: 4.7325. Min Act: -0.1700
Data Index: 6814945 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9512. Min Range: -4.9512
Max Act: 4.7325. Min Act: -0.1700
Data Index: 144886 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9512. Min Range: -4.9512
Max Act: 4.7325. Min Act: -0.1700
Data Index: 1458281 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9512. Min Range: -4.9512
Max Act: 4.7325. Min Act: -0.1700
Data Index: 2209769 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9512. Min Range: -4.9512
Max Act: 4.7012. Min Act: -0.1700
Data Index: 455260 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9512. Min Range: -4.9512
Max Act: 4.7012. Min Act: -0.1700
Data Index: 7909994 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9512. Min Range: -4.9512
Max Act: 4.7012. Min Act: -0.1700
Data Index: 6005890 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9512. Min Range: -4.9512
Max Act: 4.6699. Min Act: -0.1700
Data Index: 3431556 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9512. Min Range: -4.9512
Max Act: 4.6699. Min Act: -0.1700
Data Index: 1190250 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19