Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2128 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9718. Min Range: -6.9718
Max Act: 6.9718. Min Act: -0.1700
Data Index: 5737992 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9718. Min Range: -6.9718
Max Act: 6.7843. Min Act: -0.1700
Data Index: 159720 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9718. Min Range: -6.9718
Max Act: 6.6593. Min Act: -0.1700
Data Index: 6388155 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9718. Min Range: -6.9718
Max Act: 6.5343. Min Act: -0.1700
Data Index: 6533859 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9718. Min Range: -6.9718
Max Act: 6.5030. Min Act: -0.1700
Data Index: 1792169 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9718. Min Range: -6.9718
Max Act: 6.5030. Min Act: -0.1700
Data Index: 5574883 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9718. Min Range: -6.9718
Max Act: 6.4405. Min Act: -0.1700
Data Index: 1283133 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9718. Min Range: -6.9718
Max Act: 6.4405. Min Act: -0.1700
Data Index: 6502178 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9718. Min Range: -6.9718
Max Act: 6.4718. Min Act: -0.1700
Data Index: 1817750 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9718. Min Range: -6.9718
Max Act: 6.4405. Min Act: -0.1700
Data Index: 8475725 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9718. Min Range: -6.9718
Max Act: 6.4405. Min Act: -0.1700
Data Index: 3513072 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9718. Min Range: -6.9718
Max Act: 6.3780. Min Act: -0.1700
Data Index: 353895 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9718. Min Range: -6.9718
Max Act: 6.3780. Min Act: -0.1700
Data Index: 3507483 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9718. Min Range: -6.9718
Max Act: 6.3468. Min Act: -0.1700
Data Index: 1817751 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9718. Min Range: -6.9718
Max Act: 6.3155. Min Act: -0.1700
Data Index: 3323451 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9718. Min Range: -6.9718
Max Act: 6.2530. Min Act: -0.1700
Data Index: 7674043 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9718. Min Range: -6.9718
Max Act: 6.2218. Min Act: -0.1700
Data Index: 6599713 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9718. Min Range: -6.9718
Max Act: 6.1905. Min Act: -0.1700
Data Index: 2729070 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9718. Min Range: -6.9718
Max Act: 6.1905. Min Act: -0.1700
Data Index: 952677 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9718. Min Range: -6.9718
Max Act: 6.1905. Min Act: -0.1700
Data Index: 3615955 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19