Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3284 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4749. Min Range: -3.4749
Max Act: 3.4749. Min Act: -0.1700
Data Index: 2403564 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4749. Min Range: -3.4749
Max Act: 3.3338. Min Act: -0.1700
Data Index: 1025884 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4749. Min Range: -3.4749
Max Act: 3.3181. Min Act: -0.1700
Data Index: 1536010 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4749. Min Range: -3.4749
Max Act: 3.3024. Min Act: -0.1700
Data Index: 702057 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4749. Min Range: -3.4749
Max Act: 3.2396. Min Act: -0.1700
Data Index: 4072449 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4749. Min Range: -3.4749
Max Act: 3.2239. Min Act: -0.1700
Data Index: 1914650 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4749. Min Range: -3.4749
Max Act: 3.2239. Min Act: -0.1700
Data Index: 7215104 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4749. Min Range: -3.4749
Max Act: 3.2239. Min Act: -0.1700
Data Index: 7559701 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4749. Min Range: -3.4749
Max Act: 3.2082. Min Act: -0.1700
Data Index: 6684825 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4749. Min Range: -3.4749
Max Act: 3.2082. Min Act: -0.1700
Data Index: 1055514 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4749. Min Range: -3.4749
Max Act: 3.1610. Min Act: -0.1700
Data Index: 1340563 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4749. Min Range: -3.4749
Max Act: 3.1610. Min Act: -0.1700
Data Index: 5532222 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4749. Min Range: -3.4749
Max Act: 3.1767. Min Act: -0.1700
Data Index: 7923915 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4749. Min Range: -3.4749
Max Act: 3.1610. Min Act: -0.1700
Data Index: 6214050 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4749. Min Range: -3.4749
Max Act: 3.1137. Min Act: -0.1700
Data Index: 2388803 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4749. Min Range: -3.4749
Max Act: 3.1610. Min Act: -0.1700
Data Index: 7113757 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4749. Min Range: -3.4749
Max Act: 3.1295. Min Act: -0.1700
Data Index: 7692089 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4749. Min Range: -3.4749
Max Act: 3.1452. Min Act: -0.1700
Data Index: 7460928 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4749. Min Range: -3.4749
Max Act: 3.1295. Min Act: -0.1700
Data Index: 5378512 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4749. Min Range: -3.4749
Max Act: 3.1137. Min Act: -0.1700
Data Index: 8047856 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19