Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2016 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.5411. Min Act: -0.1700
Data Index: 5286356 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.2911. Min Act: -0.1700
Data Index: 6027805 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.2599. Min Act: -0.1700
Data Index: 8515251 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.2286. Min Act: -0.1700
Data Index: 2571086 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.2599. Min Act: -0.1700
Data Index: 1643681 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.2286. Min Act: -0.1700
Data Index: 8037388 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.1974. Min Act: -0.1700
Data Index: 6752396 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.1661. Min Act: -0.1700
Data Index: 7035850 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.1349. Min Act: -0.1700
Data Index: 7355097 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.1036. Min Act: -0.1700
Data Index: 8099898 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.1036. Min Act: -0.1700
Data Index: 7646272 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.1036. Min Act: -0.1700
Data Index: 783501 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.0724. Min Act: -0.1700
Data Index: 4751777 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.1036. Min Act: -0.1700
Data Index: 8548340 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.0724. Min Act: -0.1700
Data Index: 4216568 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.0724. Min Act: -0.1700
Data Index: 2690646 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.0724. Min Act: -0.1700
Data Index: 3650209 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.0724. Min Act: -0.1700
Data Index: 3953925 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.0099. Min Act: -0.1700
Data Index: 5881459 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5411. Min Range: -5.5411
Max Act: 5.0411. Min Act: -0.1700
Data Index: 3136709 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #19