Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 953 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2828. Min Range: -5.2828
Max Act: 5.2828. Min Act: -0.1700
Data Index: 508666 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2828. Min Range: -5.2828
Max Act: 5.1578. Min Act: -0.1700
Data Index: 4330293 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2828. Min Range: -5.2828
Max Act: 5.0640. Min Act: -0.1700
Data Index: 2382763 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2828. Min Range: -5.2828
Max Act: 5.0953. Min Act: -0.1700
Data Index: 6798109 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2828. Min Range: -5.2828
Max Act: 5.0328. Min Act: -0.1700
Data Index: 3341447 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2828. Min Range: -5.2828
Max Act: 5.0015. Min Act: -0.1700
Data Index: 1165933 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2828. Min Range: -5.2828
Max Act: 4.9390. Min Act: -0.1700
Data Index: 6347074 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2828. Min Range: -5.2828
Max Act: 4.9390. Min Act: -0.1700
Data Index: 7233427 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2828. Min Range: -5.2828
Max Act: 4.9078. Min Act: -0.1700
Data Index: 428212 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2828. Min Range: -5.2828
Max Act: 4.9390. Min Act: -0.1700
Data Index: 980103 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2828. Min Range: -5.2828
Max Act: 4.9390. Min Act: -0.1700
Data Index: 6890952 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2828. Min Range: -5.2828
Max Act: 4.9390. Min Act: -0.1700
Data Index: 3181913 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2828. Min Range: -5.2828
Max Act: 4.9390. Min Act: -0.1700
Data Index: 1495587 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2828. Min Range: -5.2828
Max Act: 4.9078. Min Act: -0.1700
Data Index: 7080615 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2828. Min Range: -5.2828
Max Act: 4.8765. Min Act: -0.1700
Data Index: 6391743 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2828. Min Range: -5.2828
Max Act: 4.8765. Min Act: -0.1700
Data Index: 80558 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2828. Min Range: -5.2828
Max Act: 4.9078. Min Act: -0.1700
Data Index: 4811296 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2828. Min Range: -5.2828
Max Act: 4.8765. Min Act: -0.1700
Data Index: 6850734 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2828. Min Range: -5.2828
Max Act: 4.8765. Min Act: -0.1700
Data Index: 4286024 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2828. Min Range: -5.2828
Max Act: 4.8453. Min Act: -0.1700
Data Index: 6241800 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19