Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3515 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.5975. Min Act: -0.1700
Data Index: 177004 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.6601. Min Act: -0.1700
Data Index: 7947253 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.5975. Min Act: -0.1700
Data Index: 6697422 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.5662. Min Act: -0.1700
Data Index: 3209028 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.5349. Min Act: -0.1700
Data Index: 3709078 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.5349. Min Act: -0.1700
Data Index: 8367959 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.5349. Min Act: -0.1700
Data Index: 1041467 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.5349. Min Act: -0.1700
Data Index: 6363906 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.5036. Min Act: -0.1700
Data Index: 1109010 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.5036. Min Act: -0.1700
Data Index: 8054465 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.4722. Min Act: -0.1700
Data Index: 7475715 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.5036. Min Act: -0.1700
Data Index: 7219064 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.5036. Min Act: -0.1700
Data Index: 48562 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.4722. Min Act: -0.1700
Data Index: 1318779 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.5349. Min Act: -0.1700
Data Index: 4821878 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.5036. Min Act: -0.1700
Data Index: 6974427 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.4722. Min Act: -0.1700
Data Index: 6995344 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.4722. Min Act: -0.1700
Data Index: 1050507 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.4722. Min Act: -0.1700
Data Index: 6824009 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6601. Min Range: -3.6601
Max Act: 3.4722. Min Act: -0.1700
Data Index: 1946316 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19