Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 912 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8530. Min Range: -5.8530
Max Act: 5.8530. Min Act: -0.1700
Data Index: 96733 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8530. Min Range: -5.8530
Max Act: 5.3843. Min Act: -0.1700
Data Index: 6655891 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8530. Min Range: -5.8530
Max Act: 5.2905. Min Act: -0.1700
Data Index: 1744511 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8530. Min Range: -5.8530
Max Act: 5.2593. Min Act: -0.1700
Data Index: 4443682 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8530. Min Range: -5.8530
Max Act: 5.1030. Min Act: -0.1700
Data Index: 488176 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8530. Min Range: -5.8530
Max Act: 5.0718. Min Act: -0.1700
Data Index: 6313526 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8530. Min Range: -5.8530
Max Act: 5.1030. Min Act: -0.1700
Data Index: 716994 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8530. Min Range: -5.8530
Max Act: 5.0718. Min Act: -0.1700
Data Index: 2071549 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8530. Min Range: -5.8530
Max Act: 5.0718. Min Act: -0.1700
Data Index: 1163255 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8530. Min Range: -5.8530
Max Act: 5.0405. Min Act: -0.1700
Data Index: 5442064 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8530. Min Range: -5.8530
Max Act: 5.0405. Min Act: -0.1700
Data Index: 5619165 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8530. Min Range: -5.8530
Max Act: 4.9780. Min Act: -0.1700
Data Index: 1139225 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8530. Min Range: -5.8530
Max Act: 4.9780. Min Act: -0.1700
Data Index: 5643844 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8530. Min Range: -5.8530
Max Act: 4.9468. Min Act: -0.1700
Data Index: 580724 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8530. Min Range: -5.8530
Max Act: 4.9780. Min Act: -0.1700
Data Index: 3520953 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8530. Min Range: -5.8530
Max Act: 4.9468. Min Act: -0.1700
Data Index: 2415781 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8530. Min Range: -5.8530
Max Act: 4.9155. Min Act: -0.1700
Data Index: 2124828 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8530. Min Range: -5.8530
Max Act: 4.9155. Min Act: -0.1700
Data Index: 5708616 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8530. Min Range: -5.8530
Max Act: 4.9468. Min Act: -0.1700
Data Index: 5365025 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8530. Min Range: -5.8530
Max Act: 4.9155. Min Act: -0.1700
Data Index: 3585019 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19