Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2221 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6434. Min Range: -7.6434
Max Act: 7.6434. Min Act: -0.1700
Data Index: 7305405 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6434. Min Range: -7.6434
Max Act: 7.5496. Min Act: -0.1700
Data Index: 4031625 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6434. Min Range: -7.6434
Max Act: 7.5809. Min Act: -0.1700
Data Index: 10427 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6434. Min Range: -7.6434
Max Act: 7.5496. Min Act: -0.1700
Data Index: 4882505 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6434. Min Range: -7.6434
Max Act: 7.4559. Min Act: -0.1700
Data Index: 1361422 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6434. Min Range: -7.6434
Max Act: 7.4559. Min Act: -0.1700
Data Index: 300253 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6434. Min Range: -7.6434
Max Act: 7.3934. Min Act: -0.1700
Data Index: 4296472 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6434. Min Range: -7.6434
Max Act: 7.3309. Min Act: -0.1700
Data Index: 727342 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6434. Min Range: -7.6434
Max Act: 7.2996. Min Act: -0.1700
Data Index: 7926 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6434. Min Range: -7.6434
Max Act: 7.2996. Min Act: -0.1700
Data Index: 5060444 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6434. Min Range: -7.6434
Max Act: 7.2371. Min Act: -0.1700
Data Index: 5305617 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6434. Min Range: -7.6434
Max Act: 7.2371. Min Act: -0.1700
Data Index: 6877792 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6434. Min Range: -7.6434
Max Act: 7.2059. Min Act: -0.1700
Data Index: 7232372 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6434. Min Range: -7.6434
Max Act: 7.2059. Min Act: -0.1700
Data Index: 8651353 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6434. Min Range: -7.6434
Max Act: 7.2059. Min Act: -0.1700
Data Index: 761990 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6434. Min Range: -7.6434
Max Act: 7.2371. Min Act: -0.1700
Data Index: 2243570 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6434. Min Range: -7.6434
Max Act: 7.2059. Min Act: -0.1700
Data Index: 2131448 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6434. Min Range: -7.6434
Max Act: 7.1746. Min Act: -0.1700
Data Index: 7428856 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6434. Min Range: -7.6434
Max Act: 7.1746. Min Act: -0.1700
Data Index: 7721892 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6434. Min Range: -7.6434
Max Act: 7.1746. Min Act: -0.1700
Data Index: 2960280 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19