Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4195 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9410. Min Range: -6.9410
Max Act: 6.9410. Min Act: -0.1700
Data Index: 3948993 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9410. Min Range: -6.9410
Max Act: 6.8473. Min Act: -0.1700
Data Index: 390394 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9410. Min Range: -6.9410
Max Act: 6.8160. Min Act: -0.1700
Data Index: 5510170 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9410. Min Range: -6.9410
Max Act: 6.8473. Min Act: -0.1700
Data Index: 2846601 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9410. Min Range: -6.9410
Max Act: 6.7848. Min Act: -0.1700
Data Index: 8024613 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9410. Min Range: -6.9410
Max Act: 6.7535. Min Act: -0.1700
Data Index: 859845 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9410. Min Range: -6.9410
Max Act: 6.7535. Min Act: -0.1700
Data Index: 6598571 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9410. Min Range: -6.9410
Max Act: 6.7223. Min Act: -0.1700
Data Index: 2309776 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9410. Min Range: -6.9410
Max Act: 6.6598. Min Act: -0.1700
Data Index: 5062711 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9410. Min Range: -6.9410
Max Act: 6.6598. Min Act: -0.1700
Data Index: 3333920 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9410. Min Range: -6.9410
Max Act: 6.5973. Min Act: -0.1700
Data Index: 5573290 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9410. Min Range: -6.9410
Max Act: 6.5973. Min Act: -0.1700
Data Index: 8675695 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9410. Min Range: -6.9410
Max Act: 6.5973. Min Act: -0.1700
Data Index: 7292632 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9410. Min Range: -6.9410
Max Act: 6.5973. Min Act: -0.1700
Data Index: 5993151 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9410. Min Range: -6.9410
Max Act: 6.5660. Min Act: -0.1700
Data Index: 3098184 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9410. Min Range: -6.9410
Max Act: 6.5660. Min Act: -0.1700
Data Index: 785193 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9410. Min Range: -6.9410
Max Act: 6.5660. Min Act: -0.1700
Data Index: 2945265 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9410. Min Range: -6.9410
Max Act: 6.5348. Min Act: -0.1700
Data Index: 6878191 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9410. Min Range: -6.9410
Max Act: 6.5035. Min Act: -0.1700
Data Index: 7292633 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9410. Min Range: -6.9410
Max Act: 6.5035. Min Act: -0.1700
Data Index: 925284 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19