Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 718 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.7738. Min Act: -0.1700
Data Index: 5436955 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.6176. Min Act: -0.1700
Data Index: 2824979 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.5238. Min Act: -0.1700
Data Index: 752357 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.5551. Min Act: -0.1700
Data Index: 560483 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.5238. Min Act: -0.1700
Data Index: 5037395 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.4926. Min Act: -0.1700
Data Index: 2413139 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.4301. Min Act: -0.1700
Data Index: 8470435 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.4926. Min Act: -0.1700
Data Index: 560488 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.4301. Min Act: -0.1700
Data Index: 4179360 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.4301. Min Act: -0.1700
Data Index: 6098967 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.3676. Min Act: -0.1700
Data Index: 6751899 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.3676. Min Act: -0.1700
Data Index: 6746270 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.3676. Min Act: -0.1700
Data Index: 3394577 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.3676. Min Act: -0.1700
Data Index: 138810 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.3363. Min Act: -0.1700
Data Index: 4546104 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.3676. Min Act: -0.1700
Data Index: 5210054 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.3676. Min Act: -0.1700
Data Index: 6789107 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.3988. Min Act: -0.1700
Data Index: 8468114 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.3676. Min Act: -0.1700
Data Index: 3631786 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7738. Min Range: -5.7738
Max Act: 5.3363. Min Act: -0.1700
Data Index: 623502 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19