Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3282 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1874. Min Range: -8.1874
Max Act: 8.1874. Min Act: -0.1700
Data Index: 3060735 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1874. Min Range: -8.1874
Max Act: 8.1249. Min Act: -0.1700
Data Index: 1428114 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1874. Min Range: -8.1874
Max Act: 8.0624. Min Act: -0.1700
Data Index: 5241318 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1874. Min Range: -8.1874
Max Act: 8.1874. Min Act: -0.1700
Data Index: 4697677 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1874. Min Range: -8.1874
Max Act: 8.1249. Min Act: -0.1700
Data Index: 4665415 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1874. Min Range: -8.1874
Max Act: 8.1249. Min Act: -0.1700
Data Index: 4359326 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1874. Min Range: -8.1874
Max Act: 8.1249. Min Act: -0.1700
Data Index: 2583210 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1874. Min Range: -8.1874
Max Act: 8.1249. Min Act: -0.1700
Data Index: 8681904 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1874. Min Range: -8.1874
Max Act: 8.0624. Min Act: -0.1700
Data Index: 3788924 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1874. Min Range: -8.1874
Max Act: 8.1249. Min Act: -0.1700
Data Index: 7346379 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1874. Min Range: -8.1874
Max Act: 8.1249. Min Act: -0.1700
Data Index: 7134323 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1874. Min Range: -8.1874
Max Act: 8.1249. Min Act: -0.1700
Data Index: 6874389 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1874. Min Range: -8.1874
Max Act: 8.0624. Min Act: -0.1700
Data Index: 5505100 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1874. Min Range: -8.1874
Max Act: 8.1249. Min Act: -0.1700
Data Index: 849957 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1874. Min Range: -8.1874
Max Act: 8.0624. Min Act: -0.1700
Data Index: 4127009 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1874. Min Range: -8.1874
Max Act: 8.0624. Min Act: -0.1700
Data Index: 1157293 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1874. Min Range: -8.1874
Max Act: 8.1249. Min Act: -0.1700
Data Index: 4220221 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1874. Min Range: -8.1874
Max Act: 8.1249. Min Act: -0.1700
Data Index: 582997 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1874. Min Range: -8.1874
Max Act: 7.9999. Min Act: -0.1700
Data Index: 4525896 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1874. Min Range: -8.1874
Max Act: 8.1249. Min Act: -0.1700
Data Index: 498196 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19