Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 833 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3515. Min Range: -6.3515
Max Act: 6.3515. Min Act: -0.1700
Data Index: 2512891 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3515. Min Range: -6.3515
Max Act: 6.2265. Min Act: -0.1700
Data Index: 2202089 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3515. Min Range: -6.3515
Max Act: 6.1640. Min Act: -0.1700
Data Index: 292587 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3515. Min Range: -6.3515
Max Act: 6.1953. Min Act: -0.1700
Data Index: 2647953 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3515. Min Range: -6.3515
Max Act: 6.1640. Min Act: -0.1699
Data Index: 2857073 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3515. Min Range: -6.3515
Max Act: 6.1640. Min Act: -0.1700
Data Index: 3897266 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3515. Min Range: -6.3515
Max Act: 6.1328. Min Act: -0.1699
Data Index: 5061849 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3515. Min Range: -6.3515
Max Act: 6.1328. Min Act: -0.1700
Data Index: 6274177 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3515. Min Range: -6.3515
Max Act: 6.1640. Min Act: -0.1700
Data Index: 5973174 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3515. Min Range: -6.3515
Max Act: 6.1328. Min Act: -0.1700
Data Index: 6649622 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3515. Min Range: -6.3515
Max Act: 6.1015. Min Act: -0.1700
Data Index: 7394825 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3515. Min Range: -6.3515
Max Act: 6.1328. Min Act: -0.1700
Data Index: 2233377 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3515. Min Range: -6.3515
Max Act: 6.1328. Min Act: -0.1700
Data Index: 351377 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3515. Min Range: -6.3515
Max Act: 6.1015. Min Act: -0.1685
Data Index: 4696734 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3515. Min Range: -6.3515
Max Act: 6.0703. Min Act: -0.1697
Data Index: 3400390 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3515. Min Range: -6.3515
Max Act: 6.0703. Min Act: -0.1700
Data Index: 5834157 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3515. Min Range: -6.3515
Max Act: 6.0703. Min Act: -0.1700
Data Index: 1398220 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3515. Min Range: -6.3515
Max Act: 6.0703. Min Act: -0.1700
Data Index: 419190 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3515. Min Range: -6.3515
Max Act: 6.0390. Min Act: -0.1700
Data Index: 470736 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3515. Min Range: -6.3515
Max Act: 6.0703. Min Act: -0.1700
Data Index: 1484246 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19