Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3390 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0746. Min Range: -8.0746
Max Act: 8.0746. Min Act: -0.1700
Data Index: 1778960 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0746. Min Range: -8.0746
Max Act: 8.0121. Min Act: -0.1700
Data Index: 5737562 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0746. Min Range: -8.0746
Max Act: 8.0121. Min Act: -0.1700
Data Index: 7456161 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0746. Min Range: -8.0746
Max Act: 7.8871. Min Act: -0.1700
Data Index: 969708 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0746. Min Range: -8.0746
Max Act: 7.9496. Min Act: -0.1700
Data Index: 3008045 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0746. Min Range: -8.0746
Max Act: 7.8871. Min Act: -0.1700
Data Index: 2920009 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0746. Min Range: -8.0746
Max Act: 7.8246. Min Act: -0.1700
Data Index: 7194521 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0746. Min Range: -8.0746
Max Act: 7.7621. Min Act: -0.1700
Data Index: 7062425 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0746. Min Range: -8.0746
Max Act: 7.7621. Min Act: -0.1700
Data Index: 4892384 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0746. Min Range: -8.0746
Max Act: 7.7621. Min Act: -0.1700
Data Index: 8115081 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0746. Min Range: -8.0746
Max Act: 7.7621. Min Act: -0.1700
Data Index: 2828636 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0746. Min Range: -8.0746
Max Act: 7.7621. Min Act: -0.1700
Data Index: 7342219 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0746. Min Range: -8.0746
Max Act: 7.7621. Min Act: -0.1700
Data Index: 1571332 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0746. Min Range: -8.0746
Max Act: 7.7621. Min Act: -0.1700
Data Index: 5532927 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0746. Min Range: -8.0746
Max Act: 7.7621. Min Act: -0.1700
Data Index: 1504868 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0746. Min Range: -8.0746
Max Act: 7.6683. Min Act: -0.1700
Data Index: 16853 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0746. Min Range: -8.0746
Max Act: 7.6683. Min Act: -0.1700
Data Index: 6583180 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0746. Min Range: -8.0746
Max Act: 7.6683. Min Act: -0.1700
Data Index: 4388467 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0746. Min Range: -8.0746
Max Act: 7.6371. Min Act: -0.1700
Data Index: 489707 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0746. Min Range: -8.0746
Max Act: 7.6371. Min Act: -0.1700
Data Index: 2901847 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #19