Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3576 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5504. Min Range: -2.5504
Max Act: 2.5504. Min Act: -0.1700
Data Index: 2163868 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5504. Min Range: -2.5504
Max Act: 2.5181. Min Act: -0.1700
Data Index: 7435463 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5504. Min Range: -2.5504
Max Act: 2.5181. Min Act: -0.1700
Data Index: 5213373 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5504. Min Range: -2.5504
Max Act: 2.5019. Min Act: -0.1700
Data Index: 2367143 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5504. Min Range: -2.5504
Max Act: 2.4695. Min Act: -0.1700
Data Index: 8468763 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5504. Min Range: -2.5504
Max Act: 2.4532. Min Act: -0.1700
Data Index: 6865683 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5504. Min Range: -2.5504
Max Act: 2.4370. Min Act: -0.1700
Data Index: 7960579 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5504. Min Range: -2.5504
Max Act: 2.4370. Min Act: -0.1700
Data Index: 8327254 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5504. Min Range: -2.5504
Max Act: 2.4370. Min Act: -0.1700
Data Index: 8205058 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5504. Min Range: -2.5504
Max Act: 2.4207. Min Act: -0.1700
Data Index: 7899558 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5504. Min Range: -2.5504
Max Act: 2.4207. Min Act: -0.1700
Data Index: 5321226 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5504. Min Range: -2.5504
Max Act: 2.4044. Min Act: -0.1700
Data Index: 8134653 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5504. Min Range: -2.5504
Max Act: 2.4044. Min Act: -0.1700
Data Index: 3481984 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5504. Min Range: -2.5504
Max Act: 2.4044. Min Act: -0.1700
Data Index: 8294063 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5504. Min Range: -2.5504
Max Act: 2.4207. Min Act: -0.1700
Data Index: 5151036 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5504. Min Range: -2.5504
Max Act: 2.3880. Min Act: -0.1700
Data Index: 1060293 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5504. Min Range: -2.5504
Max Act: 2.4044. Min Act: -0.1700
Data Index: 4770577 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5504. Min Range: -2.5504
Max Act: 2.3717. Min Act: -0.1700
Data Index: 2300581 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5504. Min Range: -2.5504
Max Act: 2.3717. Min Act: -0.1700
Data Index: 1774995 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5504. Min Range: -2.5504
Max Act: 2.3717. Min Act: -0.1700
Data Index: 6745997 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19