Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3649 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8679. Min Range: -4.8679
Max Act: 4.8679. Min Act: -0.1700
Data Index: 5691410 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8679. Min Range: -4.8679
Max Act: 4.6491. Min Act: -0.1700
Data Index: 5728909 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8679. Min Range: -4.8679
Max Act: 4.6491. Min Act: -0.1700
Data Index: 5602652 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8679. Min Range: -4.8679
Max Act: 4.5554. Min Act: -0.1700
Data Index: 5602651 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8679. Min Range: -4.8679
Max Act: 4.5554. Min Act: -0.1700
Data Index: 223877 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8679. Min Range: -4.8679
Max Act: 4.5241. Min Act: -0.1700
Data Index: 7856892 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8679. Min Range: -4.8679
Max Act: 4.4929. Min Act: -0.1700
Data Index: 1268542 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8679. Min Range: -4.8679
Max Act: 4.4616. Min Act: -0.1700
Data Index: 5602653 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8679. Min Range: -4.8679
Max Act: 4.4616. Min Act: -0.1700
Data Index: 5602646 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8679. Min Range: -4.8679
Max Act: 4.4616. Min Act: -0.1700
Data Index: 741624 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8679. Min Range: -4.8679
Max Act: 4.4616. Min Act: -0.1700
Data Index: 2971868 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8679. Min Range: -4.8679
Max Act: 4.4304. Min Act: -0.1700
Data Index: 8455986 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8679. Min Range: -4.8679
Max Act: 4.4304. Min Act: -0.1700
Data Index: 6511640 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8679. Min Range: -4.8679
Max Act: 4.3679. Min Act: -0.1700
Data Index: 4678482 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8679. Min Range: -4.8679
Max Act: 4.3991. Min Act: -0.1700
Data Index: 5981671 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8679. Min Range: -4.8679
Max Act: 4.3991. Min Act: -0.1700
Data Index: 6375677 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8679. Min Range: -4.8679
Max Act: 4.3991. Min Act: -0.1700
Data Index: 1674746 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8679. Min Range: -4.8679
Max Act: 4.3679. Min Act: -0.1700
Data Index: 6727016 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8679. Min Range: -4.8679
Max Act: 4.3366. Min Act: -0.1700
Data Index: 5340891 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8679. Min Range: -4.8679
Max Act: 4.3366. Min Act: -0.1700
Data Index: 1265620 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #19