Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2363 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0614. Min Range: -6.0614
Max Act: 6.0614. Min Act: -0.1700
Data Index: 4922926 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0614. Min Range: -6.0614
Max Act: 6.0614. Min Act: -0.1700
Data Index: 3283806 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0614. Min Range: -6.0614
Max Act: 6.0301. Min Act: -0.1700
Data Index: 7577417 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0614. Min Range: -6.0614
Max Act: 5.8739. Min Act: -0.1700
Data Index: 2929511 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0614. Min Range: -6.0614
Max Act: 5.8426. Min Act: -0.1700
Data Index: 295492 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0614. Min Range: -6.0614
Max Act: 5.7801. Min Act: -0.1700
Data Index: 5204943 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0614. Min Range: -6.0614
Max Act: 5.7489. Min Act: -0.1700
Data Index: 6069601 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0614. Min Range: -6.0614
Max Act: 5.7176. Min Act: -0.1700
Data Index: 2796 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0614. Min Range: -6.0614
Max Act: 5.6864. Min Act: -0.1700
Data Index: 2238764 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0614. Min Range: -6.0614
Max Act: 5.5926. Min Act: -0.1700
Data Index: 1572573 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0614. Min Range: -6.0614
Max Act: 5.5614. Min Act: -0.1700
Data Index: 4165167 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0614. Min Range: -6.0614
Max Act: 5.5301. Min Act: -0.1700
Data Index: 2049858 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0614. Min Range: -6.0614
Max Act: 5.5301. Min Act: -0.1700
Data Index: 7406583 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0614. Min Range: -6.0614
Max Act: 5.4989. Min Act: -0.1700
Data Index: 2642077 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0614. Min Range: -6.0614
Max Act: 5.4676. Min Act: -0.1700
Data Index: 7518757 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0614. Min Range: -6.0614
Max Act: 5.4989. Min Act: -0.1700
Data Index: 3202937 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0614. Min Range: -6.0614
Max Act: 5.4989. Min Act: -0.1700
Data Index: 1946422 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0614. Min Range: -6.0614
Max Act: 5.4676. Min Act: -0.1700
Data Index: 818504 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0614. Min Range: -6.0614
Max Act: 5.4364. Min Act: -0.1700
Data Index: 2257263 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0614. Min Range: -6.0614
Max Act: 5.4364. Min Act: -0.1700
Data Index: 6708835 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19