Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1001 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1508. Min Range: -5.1508
Max Act: 5.1508. Min Act: -0.1700
Data Index: 3697373 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1508. Min Range: -5.1508
Max Act: 5.1196. Min Act: -0.1700
Data Index: 4767712 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1508. Min Range: -5.1508
Max Act: 5.0258. Min Act: -0.1700
Data Index: 3502539 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1508. Min Range: -5.1508
Max Act: 5.0258. Min Act: -0.1700
Data Index: 5560929 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1508. Min Range: -5.1508
Max Act: 4.9946. Min Act: -0.1700
Data Index: 7651475 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1508. Min Range: -5.1508
Max Act: 4.9633. Min Act: -0.1700
Data Index: 8773015 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1508. Min Range: -5.1508
Max Act: 4.9008. Min Act: -0.1700
Data Index: 3591439 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1508. Min Range: -5.1508
Max Act: 4.9008. Min Act: -0.1700
Data Index: 7661772 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1508. Min Range: -5.1508
Max Act: 4.9008. Min Act: -0.1700
Data Index: 8832754 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1508. Min Range: -5.1508
Max Act: 4.8696. Min Act: -0.1700
Data Index: 201899 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1508. Min Range: -5.1508
Max Act: 4.8383. Min Act: -0.1700
Data Index: 5417435 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1508. Min Range: -5.1508
Max Act: 4.7758. Min Act: -0.1700
Data Index: 8663593 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1508. Min Range: -5.1508
Max Act: 4.8383. Min Act: -0.1700
Data Index: 1311816 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1508. Min Range: -5.1508
Max Act: 4.8071. Min Act: -0.1700
Data Index: 5850592 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1508. Min Range: -5.1508
Max Act: 4.8071. Min Act: -0.1700
Data Index: 5537927 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1508. Min Range: -5.1508
Max Act: 4.7758. Min Act: -0.1700
Data Index: 8271395 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1508. Min Range: -5.1508
Max Act: 4.7758. Min Act: -0.1700
Data Index: 6977342 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1508. Min Range: -5.1508
Max Act: 4.7446. Min Act: -0.1700
Data Index: 1499791 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1508. Min Range: -5.1508
Max Act: 4.7133. Min Act: -0.1700
Data Index: 5932047 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1508. Min Range: -5.1508
Max Act: 4.7133. Min Act: -0.1700
Data Index: 7673777 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #19