Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3910 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.2325. Min Act: -0.1700
Data Index: 3687013 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.1700. Min Act: -0.1700
Data Index: 5961796 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.1700. Min Act: -0.1700
Data Index: 2480424 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.1700. Min Act: -0.1700
Data Index: 6716326 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.1075. Min Act: -0.1700
Data Index: 3165652 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.1700. Min Act: -0.1700
Data Index: 5614812 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.1700. Min Act: -0.1700
Data Index: 496098 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.1387. Min Act: -0.1700
Data Index: 6887295 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.1387. Min Act: -0.1700
Data Index: 6682895 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.1075. Min Act: -0.1700
Data Index: 5052681 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.1387. Min Act: -0.1700
Data Index: 4314657 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.0762. Min Act: -0.1700
Data Index: 8321548 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.0762. Min Act: -0.1700
Data Index: 6020053 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.0762. Min Act: -0.1700
Data Index: 6766999 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.1075. Min Act: -0.1700
Data Index: 5253166 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.1075. Min Act: -0.1700
Data Index: 5092900 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.0450. Min Act: -0.1700
Data Index: 7448993 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.0762. Min Act: -0.1700
Data Index: 4160991 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.0762. Min Act: -0.1700
Data Index: 4444631 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2325. Min Range: -4.2325
Max Act: 4.0450. Min Act: -0.1700
Data Index: 2093117 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19