Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1953 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5700. Min Range: -5.5700
Max Act: 5.5700. Min Act: -0.1700
Data Index: 2875021 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5700. Min Range: -5.5700
Max Act: 5.4762. Min Act: -0.1700
Data Index: 3317074 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5700. Min Range: -5.5700
Max Act: 5.4762. Min Act: -0.1700
Data Index: 4661021 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5700. Min Range: -5.5700
Max Act: 5.4762. Min Act: -0.1700
Data Index: 17283 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5700. Min Range: -5.5700
Max Act: 5.4450. Min Act: -0.1700
Data Index: 4187457 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5700. Min Range: -5.5700
Max Act: 5.4450. Min Act: -0.1700
Data Index: 1111715 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5700. Min Range: -5.5700
Max Act: 5.4137. Min Act: -0.1700
Data Index: 5610198 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5700. Min Range: -5.5700
Max Act: 5.3825. Min Act: -0.1700
Data Index: 422609 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5700. Min Range: -5.5700
Max Act: 5.2887. Min Act: -0.1700
Data Index: 845993 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5700. Min Range: -5.5700
Max Act: 5.2575. Min Act: -0.1700
Data Index: 524438 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5700. Min Range: -5.5700
Max Act: 5.2575. Min Act: -0.1700
Data Index: 3286494 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5700. Min Range: -5.5700
Max Act: 5.2575. Min Act: -0.1700
Data Index: 4188423 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5700. Min Range: -5.5700
Max Act: 5.2262. Min Act: -0.1700
Data Index: 3867234 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5700. Min Range: -5.5700
Max Act: 5.2262. Min Act: -0.1700
Data Index: 3863749 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5700. Min Range: -5.5700
Max Act: 5.2262. Min Act: -0.1700
Data Index: 2130757 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5700. Min Range: -5.5700
Max Act: 5.1950. Min Act: -0.1700
Data Index: 3130014 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5700. Min Range: -5.5700
Max Act: 5.1637. Min Act: -0.1700
Data Index: 8332305 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5700. Min Range: -5.5700
Max Act: 5.1325. Min Act: -0.1700
Data Index: 6892150 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5700. Min Range: -5.5700
Max Act: 5.1637. Min Act: -0.1700
Data Index: 7427152 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5700. Min Range: -5.5700
Max Act: 5.1012. Min Act: -0.1700
Data Index: 1650722 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #19