Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 382 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4766. Min Range: -5.4766
Max Act: 5.4766. Min Act: -0.1700
Data Index: 7739690 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4766. Min Range: -5.4766
Max Act: 5.4766. Min Act: -0.1700
Data Index: 83328 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4766. Min Range: -5.4766
Max Act: 5.4141. Min Act: -0.1700
Data Index: 2005480 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4766. Min Range: -5.4766
Max Act: 5.3829. Min Act: -0.1700
Data Index: 370967 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4766. Min Range: -5.4766
Max Act: 5.3204. Min Act: -0.1700
Data Index: 4661949 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4766. Min Range: -5.4766
Max Act: 5.3204. Min Act: -0.1700
Data Index: 8737503 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4766. Min Range: -5.4766
Max Act: 5.2891. Min Act: -0.1700
Data Index: 8737492 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4766. Min Range: -5.4766
Max Act: 5.2891. Min Act: -0.1700
Data Index: 673200 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4766. Min Range: -5.4766
Max Act: 5.2891. Min Act: -0.1700
Data Index: 8737497 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4766. Min Range: -5.4766
Max Act: 5.2579. Min Act: -0.1700
Data Index: 8737493 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4766. Min Range: -5.4766
Max Act: 5.2579. Min Act: -0.1700
Data Index: 8737488 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4766. Min Range: -5.4766
Max Act: 5.1641. Min Act: -0.1700
Data Index: 2950254 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4766. Min Range: -5.4766
Max Act: 5.1954. Min Act: -0.1700
Data Index: 83329 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4766. Min Range: -5.4766
Max Act: 5.1016. Min Act: -0.1700
Data Index: 83323 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4766. Min Range: -5.4766
Max Act: 5.1016. Min Act: -0.1700
Data Index: 2370386 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4766. Min Range: -5.4766
Max Act: 5.0704. Min Act: -0.1700
Data Index: 2528413 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4766. Min Range: -5.4766
Max Act: 5.1329. Min Act: -0.1700
Data Index: 83324 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4766. Min Range: -5.4766
Max Act: 5.0704. Min Act: -0.1700
Data Index: 8569312 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4766. Min Range: -5.4766
Max Act: 5.0391. Min Act: -0.1700
Data Index: 8737490 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4766. Min Range: -5.4766
Max Act: 5.0704. Min Act: -0.1700
Data Index: 8737481 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19