Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3445 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2308. Min Range: -5.2308
Max Act: 5.2308. Min Act: -0.1700
Data Index: 7715709 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2308. Min Range: -5.2308
Max Act: 5.1371. Min Act: -0.1700
Data Index: 4627303 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2308. Min Range: -5.2308
Max Act: 5.1058. Min Act: -0.1700
Data Index: 6290322 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2308. Min Range: -5.2308
Max Act: 5.0746. Min Act: -0.1700
Data Index: 3208154 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2308. Min Range: -5.2308
Max Act: 5.0433. Min Act: -0.1700
Data Index: 1948496 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2308. Min Range: -5.2308
Max Act: 5.0121. Min Act: -0.1700
Data Index: 8304571 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.9496. Min Act: -0.1700
Data Index: 387760 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.9183. Min Act: -0.1700
Data Index: 7809511 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.9496. Min Act: -0.1700
Data Index: 3885740 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.9183. Min Act: -0.1700
Data Index: 4406697 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.9183. Min Act: -0.1700
Data Index: 4883621 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.9183. Min Act: -0.1700
Data Index: 753618 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.9183. Min Act: -0.1700
Data Index: 5128965 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.8558. Min Act: -0.1700
Data Index: 6115847 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.8558. Min Act: -0.1700
Data Index: 5458697 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.8558. Min Act: -0.1700
Data Index: 6349472 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.8558. Min Act: -0.1700
Data Index: 7349197 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.8246. Min Act: -0.1700
Data Index: 49116 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.8246. Min Act: -0.1700
Data Index: 5991026 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2308. Min Range: -5.2308
Max Act: 4.8246. Min Act: -0.1700
Data Index: 2776206 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19