Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2835 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.1304. Min Range: -5.1304
Max Act: 5.1304. Min Act: -0.1700
Data Index: 124200 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1304. Min Range: -5.1304
Max Act: 5.0679. Min Act: -0.1700
Data Index: 3723054 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1304. Min Range: -5.1304
Max Act: 5.0367. Min Act: -0.1700
Data Index: 6859500 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1304. Min Range: -5.1304
Max Act: 5.0054. Min Act: -0.1700
Data Index: 3390045 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1304. Min Range: -5.1304
Max Act: 4.9742. Min Act: -0.1700
Data Index: 4954561 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1304. Min Range: -5.1304
Max Act: 4.9742. Min Act: -0.1700
Data Index: 5782317 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1304. Min Range: -5.1304
Max Act: 4.9429. Min Act: -0.1700
Data Index: 7837128 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1304. Min Range: -5.1304
Max Act: 4.9429. Min Act: -0.1700
Data Index: 1190220 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1304. Min Range: -5.1304
Max Act: 4.9117. Min Act: -0.1700
Data Index: 552188 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1304. Min Range: -5.1304
Max Act: 4.9117. Min Act: -0.1700
Data Index: 7144554 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1304. Min Range: -5.1304
Max Act: 4.8804. Min Act: -0.1700
Data Index: 7653647 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1304. Min Range: -5.1304
Max Act: 4.8804. Min Act: -0.1700
Data Index: 3823368 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1304. Min Range: -5.1304
Max Act: 4.8804. Min Act: -0.1700
Data Index: 2314386 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1304. Min Range: -5.1304
Max Act: 4.8804. Min Act: -0.1700
Data Index: 3948013 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1304. Min Range: -5.1304
Max Act: 4.8804. Min Act: -0.1700
Data Index: 5589184 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1304. Min Range: -5.1304
Max Act: 4.8804. Min Act: -0.1700
Data Index: 5858815 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1304. Min Range: -5.1304
Max Act: 4.8492. Min Act: -0.1700
Data Index: 2068541 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1304. Min Range: -5.1304
Max Act: 4.8804. Min Act: -0.1700
Data Index: 3947843 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1304. Min Range: -5.1304
Max Act: 4.8492. Min Act: -0.1700
Data Index: 552186 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1304. Min Range: -5.1304
Max Act: 4.8492. Min Act: -0.1700
Data Index: 3119929 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19