Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3678 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.9122. Min Act: -0.1700
Data Index: 761969 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.8185. Min Act: -0.1700
Data Index: 1712391 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.7872. Min Act: -0.1700
Data Index: 2975364 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.5060. Min Act: -0.1700
Data Index: 3408677 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.6622. Min Act: -0.1700
Data Index: 8291049 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.5060. Min Act: -0.1700
Data Index: 4083482 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.5060. Min Act: -0.1700
Data Index: 7399076 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.4122. Min Act: -0.1700
Data Index: 4804997 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.3810. Min Act: -0.1700
Data Index: 731408 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.2872. Min Act: -0.1700
Data Index: 3396654 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.3497. Min Act: -0.1700
Data Index: 7412573 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.2560. Min Act: -0.1700
Data Index: 502077 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.2872. Min Act: -0.1700
Data Index: 4193250 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.2560. Min Act: -0.1700
Data Index: 7544768 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.2872. Min Act: -0.1700
Data Index: 8119564 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.2247. Min Act: -0.1700
Data Index: 7400170 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.2247. Min Act: -0.1700
Data Index: 8141694 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.1935. Min Act: -0.1700
Data Index: 5855164 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.1935. Min Act: -0.1700
Data Index: 5063398 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9122. Min Range: -5.9122
Max Act: 5.1310. Min Act: -0.1700
Data Index: 5007207 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19