Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3367 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 9.2624. Min Range: -9.2624
Max Act: 9.2624. Min Act: -0.1700
Data Index: 8123006 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2624. Min Range: -9.2624
Max Act: 9.1999. Min Act: -0.1700
Data Index: 5764697 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2624. Min Range: -9.2624
Max Act: 9.0124. Min Act: -0.1700
Data Index: 3659322 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2624. Min Range: -9.2624
Max Act: 8.8874. Min Act: -0.1700
Data Index: 1258318 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2624. Min Range: -9.2624
Max Act: 8.9499. Min Act: -0.1700
Data Index: 3839431 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2624. Min Range: -9.2624
Max Act: 8.8874. Min Act: -0.1700
Data Index: 1328913 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2624. Min Range: -9.2624
Max Act: 8.9499. Min Act: -0.1700
Data Index: 426461 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2624. Min Range: -9.2624
Max Act: 8.9499. Min Act: -0.1700
Data Index: 3354769 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2624. Min Range: -9.2624
Max Act: 8.8249. Min Act: -0.1700
Data Index: 6236840 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2624. Min Range: -9.2624
Max Act: 8.8249. Min Act: -0.1700
Data Index: 1920939 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2624. Min Range: -9.2624
Max Act: 8.8874. Min Act: -0.1700
Data Index: 966074 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2624. Min Range: -9.2624
Max Act: 8.7624. Min Act: -0.1700
Data Index: 7096648 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2624. Min Range: -9.2624
Max Act: 8.7624. Min Act: -0.1700
Data Index: 4732489 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2624. Min Range: -9.2624
Max Act: 8.6999. Min Act: -0.1700
Data Index: 2237895 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2624. Min Range: -9.2624
Max Act: 8.6999. Min Act: -0.1700
Data Index: 1988676 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2624. Min Range: -9.2624
Max Act: 8.7624. Min Act: -0.1700
Data Index: 2627442 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2624. Min Range: -9.2624
Max Act: 8.6374. Min Act: -0.1700
Data Index: 1433147 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2624. Min Range: -9.2624
Max Act: 8.6374. Min Act: -0.1700
Data Index: 3285924 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2624. Min Range: -9.2624
Max Act: 8.6374. Min Act: -0.1700
Data Index: 3543292 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2624. Min Range: -9.2624
Max Act: 8.6374. Min Act: -0.1700
Data Index: 1504952 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19