Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3676 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1551. Min Range: -4.1551
Max Act: 4.1551. Min Act: -0.1700
Data Index: 4079046 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1551. Min Range: -4.1551
Max Act: 4.1238. Min Act: -0.1700
Data Index: 4847729 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.9988. Min Act: -0.1700
Data Index: 4629883 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.9676. Min Act: -0.1700
Data Index: 3407772 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.9676. Min Act: -0.1700
Data Index: 1687063 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.9676. Min Act: -0.1700
Data Index: 989974 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.9363. Min Act: -0.1700
Data Index: 7749024 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.9676. Min Act: -0.1700
Data Index: 3991281 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.9050. Min Act: -0.1700
Data Index: 2080626 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.9050. Min Act: -0.1700
Data Index: 2920525 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.9050. Min Act: -0.1700
Data Index: 566539 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.8738. Min Act: -0.1700
Data Index: 702236 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.9050. Min Act: -0.1700
Data Index: 5628622 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.8425. Min Act: -0.1700
Data Index: 6794614 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.8425. Min Act: -0.1700
Data Index: 5156917 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.8425. Min Act: -0.1700
Data Index: 6493910 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.8112. Min Act: -0.1700
Data Index: 1717264 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.8112. Min Act: -0.1700
Data Index: 5628623 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.8112. Min Act: -0.1700
Data Index: 4887008 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1551. Min Range: -4.1551
Max Act: 3.8112. Min Act: -0.1700
Data Index: 4869746 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19