Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1929 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9281. Min Range: -3.9281
Max Act: 3.9281. Min Act: -0.1700
Data Index: 1543347 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9281. Min Range: -3.9281
Max Act: 3.8343. Min Act: -0.1700
Data Index: 7347421 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9281. Min Range: -3.9281
Max Act: 3.8343. Min Act: -0.1700
Data Index: 8082664 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9281. Min Range: -3.9281
Max Act: 3.7718. Min Act: -0.1700
Data Index: 6889364 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9281. Min Range: -3.9281
Max Act: 3.7718. Min Act: -0.1700
Data Index: 22265 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9281. Min Range: -3.9281
Max Act: 3.7718. Min Act: -0.1700
Data Index: 149124 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9281. Min Range: -3.9281
Max Act: 3.7718. Min Act: -0.1700
Data Index: 1358856 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9281. Min Range: -3.9281
Max Act: 3.7718. Min Act: -0.1700
Data Index: 8221272 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9281. Min Range: -3.9281
Max Act: 3.7718. Min Act: -0.1700
Data Index: 3151799 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9281. Min Range: -3.9281
Max Act: 3.7718. Min Act: -0.1700
Data Index: 5544709 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9281. Min Range: -3.9281
Max Act: 3.7405. Min Act: -0.1700
Data Index: 5613069 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9281. Min Range: -3.9281
Max Act: 3.7405. Min Act: -0.1700
Data Index: 7787245 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9281. Min Range: -3.9281
Max Act: 3.7092. Min Act: -0.1700
Data Index: 6301768 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9281. Min Range: -3.9281
Max Act: 3.6779. Min Act: -0.1700
Data Index: 3464537 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9281. Min Range: -3.9281
Max Act: 3.7092. Min Act: -0.1700
Data Index: 2074123 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9281. Min Range: -3.9281
Max Act: 3.6779. Min Act: -0.1700
Data Index: 1097033 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9281. Min Range: -3.9281
Max Act: 3.6779. Min Act: -0.1700
Data Index: 5487621 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9281. Min Range: -3.9281
Max Act: 3.7092. Min Act: -0.1700
Data Index: 6682321 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9281. Min Range: -3.9281
Max Act: 3.6779. Min Act: -0.1700
Data Index: 396309 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9281. Min Range: -3.9281
Max Act: 3.6779. Min Act: -0.1700
Data Index: 5819068 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19