Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3722 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5596. Min Range: -5.5596
Max Act: 5.5596. Min Act: -0.1700
Data Index: 4269773 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5596. Min Range: -5.5596
Max Act: 5.5596. Min Act: -0.1700
Data Index: 3592310 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5596. Min Range: -5.5596
Max Act: 5.4346. Min Act: -0.1700
Data Index: 1325561 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5596. Min Range: -5.5596
Max Act: 5.3408. Min Act: -0.1700
Data Index: 4513017 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5596. Min Range: -5.5596
Max Act: 5.3096. Min Act: -0.1700
Data Index: 5148536 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5596. Min Range: -5.5596
Max Act: 5.3096. Min Act: -0.1700
Data Index: 1377698 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5596. Min Range: -5.5596
Max Act: 5.2783. Min Act: -0.1700
Data Index: 5810865 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5596. Min Range: -5.5596
Max Act: 5.2471. Min Act: -0.1700
Data Index: 3614263 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5596. Min Range: -5.5596
Max Act: 5.2158. Min Act: -0.1700
Data Index: 3912595 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5596. Min Range: -5.5596
Max Act: 5.2158. Min Act: -0.1700
Data Index: 1744608 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5596. Min Range: -5.5596
Max Act: 5.1846. Min Act: -0.1700
Data Index: 5052218 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5596. Min Range: -5.5596
Max Act: 5.1846. Min Act: -0.1700
Data Index: 5287026 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5596. Min Range: -5.5596
Max Act: 5.1846. Min Act: -0.1700
Data Index: 1299089 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5596. Min Range: -5.5596
Max Act: 5.1533. Min Act: -0.1700
Data Index: 4642745 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5596. Min Range: -5.5596
Max Act: 5.0908. Min Act: -0.1700
Data Index: 2491523 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5596. Min Range: -5.5596
Max Act: 5.1221. Min Act: -0.1700
Data Index: 3769795 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5596. Min Range: -5.5596
Max Act: 5.1221. Min Act: -0.1700
Data Index: 3684621 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5596. Min Range: -5.5596
Max Act: 5.1221. Min Act: -0.1700
Data Index: 3605057 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5596. Min Range: -5.5596
Max Act: 5.1533. Min Act: -0.1700
Data Index: 4536825 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5596. Min Range: -5.5596
Max Act: 5.1221. Min Act: -0.1700
Data Index: 5148537 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19