Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5074 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2710. Min Range: -4.2710
Max Act: 4.2710. Min Act: -0.1700
Data Index: 661305 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2710. Min Range: -4.2710
Max Act: 4.2397. Min Act: -0.1700
Data Index: 661304 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2710. Min Range: -4.2710
Max Act: 4.1772. Min Act: -0.1700
Data Index: 7480872 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2710. Min Range: -4.2710
Max Act: 4.1772. Min Act: -0.1700
Data Index: 2792324 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2710. Min Range: -4.2710
Max Act: 4.1772. Min Act: -0.1700
Data Index: 2668989 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2710. Min Range: -4.2710
Max Act: 4.1147. Min Act: -0.1700
Data Index: 2523358 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2710. Min Range: -4.2710
Max Act: 4.0835. Min Act: -0.1700
Data Index: 4891884 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2710. Min Range: -4.2710
Max Act: 4.0522. Min Act: -0.1700
Data Index: 2957370 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2710. Min Range: -4.2710
Max Act: 4.0522. Min Act: -0.1700
Data Index: 3487752 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2710. Min Range: -4.2710
Max Act: 4.0522. Min Act: -0.1700
Data Index: 6759528 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2710. Min Range: -4.2710
Max Act: 4.0209. Min Act: -0.1700
Data Index: 7259958 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2710. Min Range: -4.2710
Max Act: 4.0209. Min Act: -0.1700
Data Index: 3946377 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2710. Min Range: -4.2710
Max Act: 4.0209. Min Act: -0.1700
Data Index: 35960 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2710. Min Range: -4.2710
Max Act: 4.0209. Min Act: -0.1700
Data Index: 661306 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2710. Min Range: -4.2710
Max Act: 3.9897. Min Act: -0.1700
Data Index: 2958656 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2710. Min Range: -4.2710
Max Act: 3.9897. Min Act: -0.1700
Data Index: 4303649 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2710. Min Range: -4.2710
Max Act: 3.9897. Min Act: -0.1700
Data Index: 6656628 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2710. Min Range: -4.2710
Max Act: 3.9584. Min Act: -0.1700
Data Index: 2621573 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2710. Min Range: -4.2710
Max Act: 3.9584. Min Act: -0.1700
Data Index: 2477623 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2710. Min Range: -4.2710
Max Act: 3.9272. Min Act: -0.1700
Data Index: 7552484 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19