Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 872 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.6948. Min Range: -10.6948
Max Act: 10.6948. Min Act: -0.1700
Data Index: 8667188 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6948. Min Range: -10.6948
Max Act: 10.6948. Min Act: -0.1700
Data Index: 860597 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6948. Min Range: -10.6948
Max Act: 10.6948. Min Act: -0.1700
Data Index: 5460908 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6948. Min Range: -10.6948
Max Act: 10.5698. Min Act: -0.1700
Data Index: 1538453 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6948. Min Range: -10.6948
Max Act: 10.6323. Min Act: -0.1700
Data Index: 5460906 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6948. Min Range: -10.6948
Max Act: 10.5073. Min Act: -0.1700
Data Index: 761345 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6948. Min Range: -10.6948
Max Act: 10.4448. Min Act: -0.1700
Data Index: 859747 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6948. Min Range: -10.6948
Max Act: 10.3823. Min Act: -0.1700
Data Index: 3049748 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6948. Min Range: -10.6948
Max Act: 10.3823. Min Act: -0.1700
Data Index: 8667187 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6948. Min Range: -10.6948
Max Act: 10.3198. Min Act: -0.1700
Data Index: 460414 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6948. Min Range: -10.6948
Max Act: 10.2573. Min Act: -0.1700
Data Index: 8560204 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6948. Min Range: -10.6948
Max Act: 10.3823. Min Act: -0.1700
Data Index: 860599 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6948. Min Range: -10.6948
Max Act: 10.2573. Min Act: -0.1700
Data Index: 8667189 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6948. Min Range: -10.6948
Max Act: 10.2573. Min Act: -0.1700
Data Index: 761346 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6948. Min Range: -10.6948
Max Act: 10.1948. Min Act: -0.1700
Data Index: 859745 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6948. Min Range: -10.6948
Max Act: 10.1323. Min Act: -0.1700
Data Index: 3049749 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6948. Min Range: -10.6948
Max Act: 10.0698. Min Act: -0.1700
Data Index: 4713536 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6948. Min Range: -10.6948
Max Act: 10.1948. Min Act: -0.1700
Data Index: 3416125 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6948. Min Range: -10.6948
Max Act: 10.1323. Min Act: -0.1700
Data Index: 8560203 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6948. Min Range: -10.6948
Max Act: 10.1323. Min Act: -0.1700
Data Index: 3049747 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19