Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3221 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4742. Min Range: -5.4742
Max Act: 5.4742. Min Act: -0.1700
Data Index: 3569588 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4742. Min Range: -5.4742
Max Act: 5.4430. Min Act: -0.1700
Data Index: 7770461 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4742. Min Range: -5.4742
Max Act: 5.3805. Min Act: -0.1700
Data Index: 1143678 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4742. Min Range: -5.4742
Max Act: 5.3492. Min Act: -0.1700
Data Index: 5581463 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4742. Min Range: -5.4742
Max Act: 5.2867. Min Act: -0.1700
Data Index: 3662001 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4742. Min Range: -5.4742
Max Act: 5.3180. Min Act: -0.1700
Data Index: 4593530 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4742. Min Range: -5.4742
Max Act: 5.2867. Min Act: -0.1700
Data Index: 7673914 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4742. Min Range: -5.4742
Max Act: 5.2867. Min Act: -0.1700
Data Index: 8212753 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4742. Min Range: -5.4742
Max Act: 5.2555. Min Act: -0.1700
Data Index: 2681513 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4742. Min Range: -5.4742
Max Act: 5.2242. Min Act: -0.1700
Data Index: 196149 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4742. Min Range: -5.4742
Max Act: 5.1930. Min Act: -0.1700
Data Index: 5197064 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4742. Min Range: -5.4742
Max Act: 5.1930. Min Act: -0.1700
Data Index: 5391144 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4742. Min Range: -5.4742
Max Act: 5.1930. Min Act: -0.1700
Data Index: 4783749 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4742. Min Range: -5.4742
Max Act: 5.1930. Min Act: -0.1700
Data Index: 4319308 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4742. Min Range: -5.4742
Max Act: 5.1930. Min Act: -0.1700
Data Index: 4373007 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4742. Min Range: -5.4742
Max Act: 5.1930. Min Act: -0.1700
Data Index: 4593288 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4742. Min Range: -5.4742
Max Act: 5.2242. Min Act: -0.1700
Data Index: 1391534 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4742. Min Range: -5.4742
Max Act: 5.1305. Min Act: -0.1700
Data Index: 3271958 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4742. Min Range: -5.4742
Max Act: 5.1617. Min Act: -0.1700
Data Index: 7566803 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4742. Min Range: -5.4742
Max Act: 5.1617. Min Act: -0.1700
Data Index: 1015901 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19