Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1529 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1648. Min Range: -7.1648
Max Act: 7.1648. Min Act: -0.1700
Data Index: 4961021 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.7586. Min Act: -0.1700
Data Index: 2107119 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.6961. Min Act: -0.1700
Data Index: 4896039 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.4773. Min Act: -0.1700
Data Index: 2675865 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.3836. Min Act: -0.1700
Data Index: 6034534 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.3836. Min Act: -0.1700
Data Index: 4670268 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.3836. Min Act: -0.1700
Data Index: 6265861 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.3523. Min Act: -0.1700
Data Index: 686336 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.3836. Min Act: -0.1700
Data Index: 1277159 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.3523. Min Act: -0.1700
Data Index: 8544386 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.3211. Min Act: -0.1700
Data Index: 1491893 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.3211. Min Act: -0.1700
Data Index: 1743181 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.3523. Min Act: -0.1700
Data Index: 8749616 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.2586. Min Act: -0.1700
Data Index: 6039706 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.3211. Min Act: -0.1700
Data Index: 2722 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.2273. Min Act: -0.1700
Data Index: 3837078 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.2586. Min Act: -0.1700
Data Index: 2878897 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.2586. Min Act: -0.1700
Data Index: 2179284 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.2273. Min Act: -0.1700
Data Index: 2113951 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.2273. Min Act: -0.1700
Data Index: 6120415 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #19