Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2844 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4657. Min Range: -3.4657
Max Act: 3.4657. Min Act: -0.1700
Data Index: 301623 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4657. Min Range: -3.4657
Max Act: 3.4500. Min Act: -0.1700
Data Index: 5518496 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4657. Min Range: -3.4657
Max Act: 3.4187. Min Act: -0.1700
Data Index: 467513 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4657. Min Range: -3.4657
Max Act: 3.3873. Min Act: -0.1700
Data Index: 1828430 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4657. Min Range: -3.4657
Max Act: 3.3403. Min Act: -0.1700
Data Index: 1325038 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4657. Min Range: -3.4657
Max Act: 3.3246. Min Act: -0.1700
Data Index: 6460558 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4657. Min Range: -3.4657
Max Act: 3.3089. Min Act: -0.1700
Data Index: 5428257 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4657. Min Range: -3.4657
Max Act: 3.3089. Min Act: -0.1700
Data Index: 5183809 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4657. Min Range: -3.4657
Max Act: 3.3089. Min Act: -0.1700
Data Index: 5820206 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4657. Min Range: -3.4657
Max Act: 3.3089. Min Act: -0.1700
Data Index: 3678989 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4657. Min Range: -3.4657
Max Act: 3.2618. Min Act: -0.1700
Data Index: 6364274 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4657. Min Range: -3.4657
Max Act: 3.2775. Min Act: -0.1700
Data Index: 177679 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4657. Min Range: -3.4657
Max Act: 3.2618. Min Act: -0.1700
Data Index: 8421867 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4657. Min Range: -3.4657
Max Act: 3.2461. Min Act: -0.1700
Data Index: 1913079 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4657. Min Range: -3.4657
Max Act: 3.2461. Min Act: -0.1700
Data Index: 6177511 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4657. Min Range: -3.4657
Max Act: 3.2461. Min Act: -0.1700
Data Index: 7754677 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4657. Min Range: -3.4657
Max Act: 3.2304. Min Act: -0.1700
Data Index: 3041707 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4657. Min Range: -3.4657
Max Act: 3.2304. Min Act: -0.1700
Data Index: 3878240 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4657. Min Range: -3.4657
Max Act: 3.2304. Min Act: -0.1700
Data Index: 5518498 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4657. Min Range: -3.4657
Max Act: 3.2146. Min Act: -0.1700
Data Index: 7478434 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19