Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6377 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6270. Min Range: -6.6270
Max Act: 6.5958. Min Act: -0.1700
Data Index: 6634587 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6270. Min Range: -6.6270
Max Act: 6.6270. Min Act: -0.1700
Data Index: 2055302 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6270. Min Range: -6.6270
Max Act: 6.5020. Min Act: -0.1700
Data Index: 575274 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6270. Min Range: -6.6270
Max Act: 6.4395. Min Act: -0.1700
Data Index: 4478970 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6270. Min Range: -6.6270
Max Act: 6.3145. Min Act: -0.1700
Data Index: 5722439 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6270. Min Range: -6.6270
Max Act: 6.3145. Min Act: -0.1700
Data Index: 8336299 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6270. Min Range: -6.6270
Max Act: 6.3458. Min Act: -0.1700
Data Index: 1365129 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6270. Min Range: -6.6270
Max Act: 6.2520. Min Act: -0.1700
Data Index: 11026 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6270. Min Range: -6.6270
Max Act: 6.1895. Min Act: -0.1700
Data Index: 7119119 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6270. Min Range: -6.6270
Max Act: 6.1270. Min Act: -0.1700
Data Index: 30619 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6270. Min Range: -6.6270
Max Act: 6.1270. Min Act: -0.1700
Data Index: 7786501 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6270. Min Range: -6.6270
Max Act: 6.0958. Min Act: -0.1700
Data Index: 7306536 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6270. Min Range: -6.6270
Max Act: 6.0958. Min Act: -0.1700
Data Index: 6467077 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6270. Min Range: -6.6270
Max Act: 6.0958. Min Act: -0.1700
Data Index: 451501 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6270. Min Range: -6.6270
Max Act: 6.0333. Min Act: -0.1700
Data Index: 4946444 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6270. Min Range: -6.6270
Max Act: 6.0333. Min Act: -0.1700
Data Index: 5833574 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6270. Min Range: -6.6270
Max Act: 6.0958. Min Act: -0.1700
Data Index: 1753374 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6270. Min Range: -6.6270
Max Act: 6.0958. Min Act: -0.1700
Data Index: 7367126 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6270. Min Range: -6.6270
Max Act: 6.0020. Min Act: -0.1700
Data Index: 3858023 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6270. Min Range: -6.6270
Max Act: 6.0333. Min Act: -0.1700
Data Index: 57168 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19