Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4759 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.3599. Min Act: -0.1700
Data Index: 4412784 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.2974. Min Act: -0.1700
Data Index: 2706381 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.2974. Min Act: -0.1700
Data Index: 1697416 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.2974. Min Act: -0.1700
Data Index: 6645909 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.2662. Min Act: -0.1700
Data Index: 1894767 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.2349. Min Act: -0.1700
Data Index: 2992270 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.2349. Min Act: -0.1700
Data Index: 1393938 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.2349. Min Act: -0.1700
Data Index: 7503563 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.1724. Min Act: -0.1700
Data Index: 4067303 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.1724. Min Act: -0.1700
Data Index: 3449116 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.2037. Min Act: -0.1699
Data Index: 8794581 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.1724. Min Act: -0.1700
Data Index: 7215185 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.1099. Min Act: -0.1700
Data Index: 3459498 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.1412. Min Act: -0.1700
Data Index: 6170406 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.1412. Min Act: -0.1700
Data Index: 7317076 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.1412. Min Act: -0.1700
Data Index: 2405205 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.1412. Min Act: -0.1700
Data Index: 6241393 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.1412. Min Act: -0.1700
Data Index: 6529381 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.1412. Min Act: -0.1700
Data Index: 6524711 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3599. Min Range: -5.3599
Max Act: 5.1724. Min Act: -0.1700
Data Index: 4930766 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #19