Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3188 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.3115. Min Range: -8.3115
Max Act: 8.3115. Min Act: -0.1700
Data Index: 7092879 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3115. Min Range: -8.3115
Max Act: 8.1240. Min Act: -0.1700
Data Index: 1780285 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3115. Min Range: -8.3115
Max Act: 7.9990. Min Act: -0.1700
Data Index: 6078496 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3115. Min Range: -8.3115
Max Act: 8.0303. Min Act: -0.1700
Data Index: 8313399 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3115. Min Range: -8.3115
Max Act: 8.0303. Min Act: -0.1700
Data Index: 8673335 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3115. Min Range: -8.3115
Max Act: 7.9678. Min Act: -0.1700
Data Index: 5489174 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3115. Min Range: -8.3115
Max Act: 7.9678. Min Act: -0.1700
Data Index: 3428382 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3115. Min Range: -8.3115
Max Act: 7.9678. Min Act: -0.1700
Data Index: 6995715 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3115. Min Range: -8.3115
Max Act: 7.9365. Min Act: -0.1700
Data Index: 4903905 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3115. Min Range: -8.3115
Max Act: 7.9365. Min Act: -0.1700
Data Index: 1461465 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3115. Min Range: -8.3115
Max Act: 7.8740. Min Act: -0.1700
Data Index: 3211362 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3115. Min Range: -8.3115
Max Act: 7.8740. Min Act: -0.1700
Data Index: 2315069 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3115. Min Range: -8.3115
Max Act: 7.8740. Min Act: -0.1700
Data Index: 5596087 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3115. Min Range: -8.3115
Max Act: 7.8115. Min Act: -0.1700
Data Index: 2413431 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3115. Min Range: -8.3115
Max Act: 7.7178. Min Act: -0.1700
Data Index: 7798896 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3115. Min Range: -8.3115
Max Act: 7.8115. Min Act: -0.1700
Data Index: 3772639 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3115. Min Range: -8.3115
Max Act: 7.8428. Min Act: -0.1700
Data Index: 7893928 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3115. Min Range: -8.3115
Max Act: 7.8115. Min Act: -0.1700
Data Index: 3170966 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3115. Min Range: -8.3115
Max Act: 7.7490. Min Act: -0.1700
Data Index: 6120545 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3115. Min Range: -8.3115
Max Act: 7.6865. Min Act: -0.1700
Data Index: 1161160 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19