Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1995 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9238. Min Range: -3.9238
Max Act: 3.9238. Min Act: -0.1700
Data Index: 1704555 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9238. Min Range: -3.9238
Max Act: 3.8925. Min Act: -0.1700
Data Index: 4369577 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9238. Min Range: -3.9238
Max Act: 3.8613. Min Act: -0.1700
Data Index: 2054093 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9238. Min Range: -3.9238
Max Act: 3.8613. Min Act: -0.1700
Data Index: 1958783 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9238. Min Range: -3.9238
Max Act: 3.8144. Min Act: -0.1700
Data Index: 8542320 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9238. Min Range: -3.9238
Max Act: 3.8300. Min Act: -0.1700
Data Index: 5461979 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9238. Min Range: -3.9238
Max Act: 3.8144. Min Act: -0.1700
Data Index: 4246708 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9238. Min Range: -3.9238
Max Act: 3.7831. Min Act: -0.1700
Data Index: 4520465 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9238. Min Range: -3.9238
Max Act: 3.7674. Min Act: -0.1700
Data Index: 5607027 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9238. Min Range: -3.9238
Max Act: 3.7362. Min Act: -0.1700
Data Index: 5132736 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9238. Min Range: -3.9238
Max Act: 3.7362. Min Act: -0.1700
Data Index: 4613984 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9238. Min Range: -3.9238
Max Act: 3.7362. Min Act: -0.1700
Data Index: 3358047 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9238. Min Range: -3.9238
Max Act: 3.7205. Min Act: -0.1700
Data Index: 2867260 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9238. Min Range: -3.9238
Max Act: 3.7205. Min Act: -0.1700
Data Index: 2371752 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9238. Min Range: -3.9238
Max Act: 3.7049. Min Act: -0.1700
Data Index: 3260945 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9238. Min Range: -3.9238
Max Act: 3.6892. Min Act: -0.1700
Data Index: 5001321 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9238. Min Range: -3.9238
Max Act: 3.7049. Min Act: -0.1700
Data Index: 5948816 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9238. Min Range: -3.9238
Max Act: 3.6736. Min Act: -0.1700
Data Index: 6586066 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9238. Min Range: -3.9238
Max Act: 3.6736. Min Act: -0.1700
Data Index: 5136054 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9238. Min Range: -3.9238
Max Act: 3.6736. Min Act: -0.1700
Data Index: 2208013 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19