Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2139 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0902. Min Range: -8.0902
Max Act: 8.0902. Min Act: -0.1699
Data Index: 5362069 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0902. Min Range: -8.0902
Max Act: 8.0277. Min Act: -0.1700
Data Index: 6380059 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0902. Min Range: -8.0902
Max Act: 8.0277. Min Act: -0.1700
Data Index: 2634811 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0902. Min Range: -8.0902
Max Act: 8.0277. Min Act: -0.1700
Data Index: 2492961 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0902. Min Range: -8.0902
Max Act: 7.9652. Min Act: -0.1700
Data Index: 2887317 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0902. Min Range: -8.0902
Max Act: 7.9652. Min Act: -0.1700
Data Index: 3149833 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0902. Min Range: -8.0902
Max Act: 7.9027. Min Act: -0.1700
Data Index: 1331665 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0902. Min Range: -8.0902
Max Act: 7.9027. Min Act: -0.1700
Data Index: 2704200 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0902. Min Range: -8.0902
Max Act: 7.9027. Min Act: -0.1700
Data Index: 4621114 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0902. Min Range: -8.0902
Max Act: 7.8402. Min Act: -0.1700
Data Index: 5494906 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0902. Min Range: -8.0902
Max Act: 7.8402. Min Act: -0.1700
Data Index: 3666502 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0902. Min Range: -8.0902
Max Act: 7.8402. Min Act: -0.1700
Data Index: 5627680 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0902. Min Range: -8.0902
Max Act: 7.8402. Min Act: -0.1700
Data Index: 496847 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0902. Min Range: -8.0902
Max Act: 7.8402. Min Act: -0.1700
Data Index: 625041 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0902. Min Range: -8.0902
Max Act: 7.8402. Min Act: -0.1700
Data Index: 3764999 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0902. Min Range: -8.0902
Max Act: 7.8402. Min Act: -0.1700
Data Index: 3330040 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0902. Min Range: -8.0902
Max Act: 7.8402. Min Act: -0.1700
Data Index: 2095540 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0902. Min Range: -8.0902
Max Act: 7.7777. Min Act: -0.1700
Data Index: 1211796 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0902. Min Range: -8.0902
Max Act: 7.7777. Min Act: -0.1700
Data Index: 4298579 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0902. Min Range: -8.0902
Max Act: 7.7777. Min Act: -0.1700
Data Index: 5985655 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19