Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1694 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.5872. Min Range: -3.5872
Max Act: 3.5872. Min Act: -0.1700
Data Index: 6124197 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5872. Min Range: -3.5872
Max Act: 3.5715. Min Act: -0.1700
Data Index: 5477182 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5872. Min Range: -3.5872
Max Act: 3.5559. Min Act: -0.1700
Data Index: 6404611 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5872. Min Range: -3.5872
Max Act: 3.5402. Min Act: -0.1700
Data Index: 392897 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5872. Min Range: -3.5872
Max Act: 3.5246. Min Act: -0.1700
Data Index: 7187139 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5872. Min Range: -3.5872
Max Act: 3.5089. Min Act: -0.1700
Data Index: 2329123 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5872. Min Range: -3.5872
Max Act: 3.5089. Min Act: -0.1700
Data Index: 1910959 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5872. Min Range: -3.5872
Max Act: 3.5089. Min Act: -0.1700
Data Index: 3503204 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5872. Min Range: -3.5872
Max Act: 3.4932. Min Act: -0.1700
Data Index: 8204728 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5872. Min Range: -3.5872
Max Act: 3.4776. Min Act: -0.1700
Data Index: 4087146 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5872. Min Range: -3.5872
Max Act: 3.4619. Min Act: -0.1700
Data Index: 7547761 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5872. Min Range: -3.5872
Max Act: 3.4306. Min Act: -0.1700
Data Index: 5206399 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5872. Min Range: -3.5872
Max Act: 3.4619. Min Act: -0.1700
Data Index: 8468058 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5872. Min Range: -3.5872
Max Act: 3.4462. Min Act: -0.1700
Data Index: 7260896 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5872. Min Range: -3.5872
Max Act: 3.4149. Min Act: -0.1700
Data Index: 5859615 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5872. Min Range: -3.5872
Max Act: 3.4149. Min Act: -0.1700
Data Index: 5435436 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5872. Min Range: -3.5872
Max Act: 3.3992. Min Act: -0.1700
Data Index: 2466923 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5872. Min Range: -3.5872
Max Act: 3.3835. Min Act: -0.1700
Data Index: 8045630 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5872. Min Range: -3.5872
Max Act: 3.3992. Min Act: -0.1700
Data Index: 857603 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5872. Min Range: -3.5872
Max Act: 3.3992. Min Act: -0.1700
Data Index: 5600870 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #19