Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5537 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0450. Min Range: -6.0450
Max Act: 6.0450. Min Act: -0.1700
Data Index: 3553616 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0450. Min Range: -6.0450
Max Act: 5.8575. Min Act: -0.1700
Data Index: 7582030 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0450. Min Range: -6.0450
Max Act: 5.8575. Min Act: -0.1700
Data Index: 3068323 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0450. Min Range: -6.0450
Max Act: 5.7950. Min Act: -0.1700
Data Index: 3159957 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0450. Min Range: -6.0450
Max Act: 5.8263. Min Act: -0.1700
Data Index: 7904741 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0450. Min Range: -6.0450
Max Act: 5.7325. Min Act: -0.1700
Data Index: 7437114 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0450. Min Range: -6.0450
Max Act: 5.7325. Min Act: -0.1700
Data Index: 1482763 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0450. Min Range: -6.0450
Max Act: 5.7013. Min Act: -0.1700
Data Index: 5376726 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0450. Min Range: -6.0450
Max Act: 5.7013. Min Act: -0.1700
Data Index: 4592448 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0450. Min Range: -6.0450
Max Act: 5.6388. Min Act: -0.1700
Data Index: 5492244 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0450. Min Range: -6.0450
Max Act: 5.6388. Min Act: -0.1700
Data Index: 7904743 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0450. Min Range: -6.0450
Max Act: 5.5763. Min Act: -0.1700
Data Index: 7904742 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0450. Min Range: -6.0450
Max Act: 5.5450. Min Act: -0.1700
Data Index: 721006 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0450. Min Range: -6.0450
Max Act: 5.5450. Min Act: -0.1700
Data Index: 5986445 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0450. Min Range: -6.0450
Max Act: 5.5450. Min Act: -0.1700
Data Index: 6353082 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0450. Min Range: -6.0450
Max Act: 5.4513. Min Act: -0.1700
Data Index: 5423139 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0450. Min Range: -6.0450
Max Act: 5.4513. Min Act: -0.1700
Data Index: 7904744 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0450. Min Range: -6.0450
Max Act: 5.4513. Min Act: -0.1700
Data Index: 5059001 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0450. Min Range: -6.0450
Max Act: 5.4825. Min Act: -0.1700
Data Index: 355146 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0450. Min Range: -6.0450
Max Act: 5.4513. Min Act: -0.1700
Data Index: 6616222 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19