Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2005 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1388. Min Range: -3.1388
Max Act: 3.1388. Min Act: -0.1700
Data Index: 7154763 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1388. Min Range: -3.1388
Max Act: 3.1230. Min Act: -0.1700
Data Index: 584359 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1388. Min Range: -3.1388
Max Act: 3.0915. Min Act: -0.1700
Data Index: 221612 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1388. Min Range: -3.1388
Max Act: 3.0915. Min Act: -0.1700
Data Index: 1209807 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1388. Min Range: -3.1388
Max Act: 3.0915. Min Act: -0.1700
Data Index: 40295 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1388. Min Range: -3.1388
Max Act: 3.0757. Min Act: -0.1700
Data Index: 4441306 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1388. Min Range: -3.1388
Max Act: 3.0600. Min Act: -0.1700
Data Index: 8396301 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.9968. Min Act: -0.1700
Data Index: 6554494 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.9810. Min Act: -0.1700
Data Index: 5131467 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.9493. Min Act: -0.1700
Data Index: 7804661 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.9493. Min Act: -0.1700
Data Index: 8300992 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.9335. Min Act: -0.1700
Data Index: 1764773 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.9335. Min Act: -0.1700
Data Index: 1112744 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.9335. Min Act: -0.1700
Data Index: 4713738 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.8860. Min Act: -0.1700
Data Index: 2663286 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.9018. Min Act: -0.1700
Data Index: 6582198 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.9018. Min Act: -0.1700
Data Index: 3931321 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.8860. Min Act: -0.1700
Data Index: 2964751 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.8860. Min Act: -0.1700
Data Index: 1766793 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1388. Min Range: -3.1388
Max Act: 2.8860. Min Act: -0.1700
Data Index: 3332562 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19