Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 785 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.8908. Min Act: -0.1700
Data Index: 6703228 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.8595. Min Act: -0.1700
Data Index: 446487 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.8439. Min Act: -0.1700
Data Index: 3666810 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.8126. Min Act: -0.1700
Data Index: 4652210 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.7188. Min Act: -0.1700
Data Index: 6899211 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.7031. Min Act: -0.1700
Data Index: 6836712 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.6718. Min Act: -0.1700
Data Index: 4619420 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.6562. Min Act: -0.1700
Data Index: 6011350 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.6405. Min Act: -0.1700
Data Index: 5032636 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.6405. Min Act: -0.1700
Data Index: 4844547 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.6092. Min Act: -0.1700
Data Index: 446488 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.5936. Min Act: -0.1700
Data Index: 4330972 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.5936. Min Act: -0.1700
Data Index: 5869820 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.6249. Min Act: -0.1700
Data Index: 6703208 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.5936. Min Act: -0.1700
Data Index: 5071854 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.5936. Min Act: -0.1700
Data Index: 559129 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.5936. Min Act: -0.1700
Data Index: 62509 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.5936. Min Act: -0.1700
Data Index: 8102763 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.5779. Min Act: -0.1700
Data Index: 446489 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.5779. Min Act: -0.1700
Data Index: 237309 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19