Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 198 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0827. Min Range: -4.0827
Max Act: 4.0827. Min Act: -0.1700
Data Index: 1734554 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0827. Min Range: -4.0827
Max Act: 4.0202. Min Act: -0.1700
Data Index: 5929446 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.9889. Min Act: -0.1700
Data Index: 3480375 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.9889. Min Act: -0.1700
Data Index: 6734555 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.9264. Min Act: -0.1700
Data Index: 505106 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.9577. Min Act: -0.1700
Data Index: 1247033 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.8951. Min Act: -0.1700
Data Index: 5887794 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.8013. Min Act: -0.1700
Data Index: 2565821 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.8326. Min Act: -0.1700
Data Index: 1774649 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.8013. Min Act: -0.1700
Data Index: 3550270 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.8170. Min Act: -0.1700
Data Index: 952229 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.8170. Min Act: -0.1700
Data Index: 1258542 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.8013. Min Act: -0.1700
Data Index: 5404530 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.7544. Min Act: -0.1700
Data Index: 6671517 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.7388. Min Act: -0.1700
Data Index: 476101 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.7388. Min Act: -0.1700
Data Index: 3023279 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.7700. Min Act: -0.1700
Data Index: 412939 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.7388. Min Act: -0.1700
Data Index: 6710804 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.7231. Min Act: -0.1700
Data Index: 8205295 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0827. Min Range: -4.0827
Max Act: 3.7388. Min Act: -0.1700
Data Index: 588897 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19