Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 980 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1783. Min Range: -8.1783
Max Act: 8.1783. Min Act: -0.1700
Data Index: 2352389 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1783. Min Range: -8.1783
Max Act: 8.1158. Min Act: -0.1700
Data Index: 464117 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1783. Min Range: -8.1783
Max Act: 7.9283. Min Act: -0.1700
Data Index: 1810597 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1783. Min Range: -8.1783
Max Act: 7.9283. Min Act: -0.1700
Data Index: 4796255 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1783. Min Range: -8.1783
Max Act: 7.8033. Min Act: -0.1700
Data Index: 5452500 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1783. Min Range: -8.1783
Max Act: 7.8033. Min Act: -0.1700
Data Index: 1484407 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1783. Min Range: -8.1783
Max Act: 7.8033. Min Act: -0.1700
Data Index: 8348400 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1783. Min Range: -8.1783
Max Act: 7.8033. Min Act: -0.1700
Data Index: 2653790 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1783. Min Range: -8.1783
Max Act: 7.8033. Min Act: -0.1700
Data Index: 4311820 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1783. Min Range: -8.1783
Max Act: 7.8033. Min Act: -0.1700
Data Index: 927712 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1783. Min Range: -8.1783
Max Act: 7.7408. Min Act: -0.1700
Data Index: 6523736 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1783. Min Range: -8.1783
Max Act: 7.6158. Min Act: -0.1700
Data Index: 7467879 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1783. Min Range: -8.1783
Max Act: 7.6783. Min Act: -0.1700
Data Index: 963944 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1783. Min Range: -8.1783
Max Act: 7.6783. Min Act: -0.1700
Data Index: 8241979 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1783. Min Range: -8.1783
Max Act: 7.6158. Min Act: -0.1700
Data Index: 1018593 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1783. Min Range: -8.1783
Max Act: 7.5533. Min Act: -0.1700
Data Index: 6094742 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1783. Min Range: -8.1783
Max Act: 7.6158. Min Act: -0.1700
Data Index: 3752757 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1783. Min Range: -8.1783
Max Act: 7.5533. Min Act: -0.1700
Data Index: 1766797 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1783. Min Range: -8.1783
Max Act: 7.5533. Min Act: -0.1700
Data Index: 2907877 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1783. Min Range: -8.1783
Max Act: 7.6158. Min Act: -0.1700
Data Index: 5018747 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19