Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2833 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9833. Min Range: -4.9833
Max Act: 4.9833. Min Act: -0.1700
Data Index: 342553 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9833. Min Range: -4.9833
Max Act: 4.9520. Min Act: -0.1700
Data Index: 3205806 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9833. Min Range: -4.9833
Max Act: 4.9208. Min Act: -0.1700
Data Index: 2710946 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9833. Min Range: -4.9833
Max Act: 4.8895. Min Act: -0.1700
Data Index: 2381498 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9833. Min Range: -4.9833
Max Act: 4.9520. Min Act: -0.1700
Data Index: 380724 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9833. Min Range: -4.9833
Max Act: 4.8895. Min Act: -0.1700
Data Index: 2199871 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9833. Min Range: -4.9833
Max Act: 4.9208. Min Act: -0.1700
Data Index: 2569244 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9833. Min Range: -4.9833
Max Act: 4.8270. Min Act: -0.1700
Data Index: 8685016 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9833. Min Range: -4.9833
Max Act: 4.8583. Min Act: -0.1700
Data Index: 2755220 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9833. Min Range: -4.9833
Max Act: 4.8270. Min Act: -0.1700
Data Index: 1302678 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9833. Min Range: -4.9833
Max Act: 4.7958. Min Act: -0.1700
Data Index: 3086623 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9833. Min Range: -4.9833
Max Act: 4.7958. Min Act: -0.1700
Data Index: 5204376 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9833. Min Range: -4.9833
Max Act: 4.7645. Min Act: -0.1700
Data Index: 3155695 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9833. Min Range: -4.9833
Max Act: 4.7645. Min Act: -0.1700
Data Index: 6955344 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9833. Min Range: -4.9833
Max Act: 4.7645. Min Act: -0.1700
Data Index: 2088028 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9833. Min Range: -4.9833
Max Act: 4.7645. Min Act: -0.1700
Data Index: 671634 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9833. Min Range: -4.9833
Max Act: 4.7958. Min Act: -0.1700
Data Index: 6786397 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9833. Min Range: -4.9833
Max Act: 4.7645. Min Act: -0.1700
Data Index: 1071995 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9833. Min Range: -4.9833
Max Act: 4.7645. Min Act: -0.1700
Data Index: 342554 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9833. Min Range: -4.9833
Max Act: 4.7645. Min Act: -0.1700
Data Index: 4778802 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19