Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1811 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1683. Min Range: -5.1683
Max Act: 5.1683. Min Act: -0.1700
Data Index: 6875929 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1683. Min Range: -5.1683
Max Act: 5.0746. Min Act: -0.1700
Data Index: 2653297 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1683. Min Range: -5.1683
Max Act: 5.0433. Min Act: -0.1700
Data Index: 177196 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1683. Min Range: -5.1683
Max Act: 4.9808. Min Act: -0.1700
Data Index: 1873394 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1683. Min Range: -5.1683
Max Act: 4.9496. Min Act: -0.1700
Data Index: 4374175 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1683. Min Range: -5.1683
Max Act: 4.9183. Min Act: -0.1700
Data Index: 4467822 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1683. Min Range: -5.1683
Max Act: 4.8871. Min Act: -0.1700
Data Index: 4796474 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1683. Min Range: -5.1683
Max Act: 4.8558. Min Act: -0.1700
Data Index: 3214055 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1683. Min Range: -5.1683
Max Act: 4.8558. Min Act: -0.1700
Data Index: 8363863 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1683. Min Range: -5.1683
Max Act: 4.8246. Min Act: -0.1700
Data Index: 119220 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1683. Min Range: -5.1683
Max Act: 4.8246. Min Act: -0.1700
Data Index: 8101158 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1683. Min Range: -5.1683
Max Act: 4.7621. Min Act: -0.1700
Data Index: 998801 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1683. Min Range: -5.1683
Max Act: 4.7621. Min Act: -0.1700
Data Index: 468680 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1683. Min Range: -5.1683
Max Act: 4.7621. Min Act: -0.1700
Data Index: 7650016 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1683. Min Range: -5.1683
Max Act: 4.7621. Min Act: -0.1700
Data Index: 1136709 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1683. Min Range: -5.1683
Max Act: 4.7308. Min Act: -0.1700
Data Index: 132008 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1683. Min Range: -5.1683
Max Act: 4.7308. Min Act: -0.1700
Data Index: 3995963 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1683. Min Range: -5.1683
Max Act: 4.7308. Min Act: -0.1700
Data Index: 7371386 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1683. Min Range: -5.1683
Max Act: 4.7308. Min Act: -0.1700
Data Index: 2123945 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1683. Min Range: -5.1683
Max Act: 4.7308. Min Act: -0.1700
Data Index: 7620910 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19