Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3564 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4256. Min Range: -8.4256
Max Act: 8.4256. Min Act: -0.1700
Data Index: 5745712 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4256. Min Range: -8.4256
Max Act: 8.2381. Min Act: -0.1700
Data Index: 212884 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4256. Min Range: -8.4256
Max Act: 8.2381. Min Act: -0.1700
Data Index: 1998977 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4256. Min Range: -8.4256
Max Act: 8.1444. Min Act: -0.1700
Data Index: 5638690 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4256. Min Range: -8.4256
Max Act: 8.1444. Min Act: -0.1700
Data Index: 3404186 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4256. Min Range: -8.4256
Max Act: 8.0819. Min Act: -0.1700
Data Index: 3193592 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4256. Min Range: -8.4256
Max Act: 8.0506. Min Act: -0.1700
Data Index: 290216 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4256. Min Range: -8.4256
Max Act: 8.0194. Min Act: -0.1700
Data Index: 4930341 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4256. Min Range: -8.4256
Max Act: 7.9881. Min Act: -0.1700
Data Index: 5507749 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4256. Min Range: -8.4256
Max Act: 7.9881. Min Act: -0.1700
Data Index: 7070589 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4256. Min Range: -8.4256
Max Act: 7.9881. Min Act: -0.1700
Data Index: 7758098 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4256. Min Range: -8.4256
Max Act: 7.9569. Min Act: -0.1700
Data Index: 7512552 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4256. Min Range: -8.4256
Max Act: 7.9256. Min Act: -0.1700
Data Index: 5495546 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4256. Min Range: -8.4256
Max Act: 7.9256. Min Act: -0.1700
Data Index: 695126 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4256. Min Range: -8.4256
Max Act: 7.8631. Min Act: -0.1700
Data Index: 4384636 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4256. Min Range: -8.4256
Max Act: 7.8631. Min Act: -0.1700
Data Index: 5133349 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4256. Min Range: -8.4256
Max Act: 7.8319. Min Act: -0.1700
Data Index: 6331459 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4256. Min Range: -8.4256
Max Act: 7.8319. Min Act: -0.1700
Data Index: 4358459 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4256. Min Range: -8.4256
Max Act: 7.8319. Min Act: -0.1700
Data Index: 304929 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4256. Min Range: -8.4256
Max Act: 7.8006. Min Act: -0.1700
Data Index: 550500 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19