Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2745 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1329. Min Range: -6.1329
Max Act: 6.1329. Min Act: -0.1698
Data Index: 2196127 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1329. Min Range: -6.1329
Max Act: 5.6641. Min Act: -0.1700
Data Index: 7528901 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1329. Min Range: -6.1329
Max Act: 5.5391. Min Act: -0.1700
Data Index: 666587 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1329. Min Range: -6.1329
Max Act: 5.5079. Min Act: -0.1698
Data Index: 6750952 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1329. Min Range: -6.1329
Max Act: 5.4766. Min Act: -0.1699
Data Index: 5556940 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1329. Min Range: -6.1329
Max Act: 5.4141. Min Act: -0.1699
Data Index: 2063509 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1329. Min Range: -6.1329
Max Act: 5.4454. Min Act: -0.1700
Data Index: 6832151 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1329. Min Range: -6.1329
Max Act: 5.3829. Min Act: -0.1700
Data Index: 1509812 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1329. Min Range: -6.1329
Max Act: 5.4141. Min Act: -0.1700
Data Index: 8283274 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1329. Min Range: -6.1329
Max Act: 5.2891. Min Act: -0.1700
Data Index: 5423900 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1329. Min Range: -6.1329
Max Act: 5.3204. Min Act: -0.1700
Data Index: 7056979 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1329. Min Range: -6.1329
Max Act: 5.3516. Min Act: -0.1700
Data Index: 1377669 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1329. Min Range: -6.1329
Max Act: 5.2891. Min Act: -0.1700
Data Index: 5986580 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1329. Min Range: -6.1329
Max Act: 5.2891. Min Act: -0.1700
Data Index: 5019889 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1329. Min Range: -6.1329
Max Act: 5.2891. Min Act: -0.1700
Data Index: 333180 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1329. Min Range: -6.1329
Max Act: 5.2579. Min Act: -0.1700
Data Index: 5426704 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1329. Min Range: -6.1329
Max Act: 5.2891. Min Act: -0.1700
Data Index: 6310733 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1329. Min Range: -6.1329
Max Act: 5.1954. Min Act: -0.1700
Data Index: 3824554 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1329. Min Range: -6.1329
Max Act: 5.1329. Min Act: -0.1700
Data Index: 3855822 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1329. Min Range: -6.1329
Max Act: 5.1641. Min Act: -0.1699
Data Index: 4991759 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #19