Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 985 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.1493. Min Range: -1.1493
Max Act: 1.1493. Min Act: -0.1700
Data Index: 7325908 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1493. Min Range: -1.1493
Max Act: 1.1405. Min Act: -0.1667
Data Index: 183672 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1493. Min Range: -1.1493
Max Act: 1.1317. Min Act: -0.1634
Data Index: 3942936 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1493. Min Range: -1.1493
Max Act: 1.1317. Min Act: -0.1700
Data Index: 4064166 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1493. Min Range: -1.1493
Max Act: 1.1229. Min Act: -0.1681
Data Index: 1605482 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1493. Min Range: -1.1493
Max Act: 1.1229. Min Act: -0.1667
Data Index: 3580733 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1493. Min Range: -1.1493
Max Act: 1.1229. Min Act: -0.1491
Data Index: 7535088 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1493. Min Range: -1.1493
Max Act: 1.1142. Min Act: -0.1681
Data Index: 1925038 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1493. Min Range: -1.1493
Max Act: 1.1054. Min Act: -0.1694
Data Index: 4478539 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1493. Min Range: -1.1493
Max Act: 1.1054. Min Act: -0.1700
Data Index: 4509617 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1493. Min Range: -1.1493
Max Act: 1.0879. Min Act: -0.1700
Data Index: 8404010 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1493. Min Range: -1.1493
Max Act: 1.0966. Min Act: -0.1677
Data Index: 8478216 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1493. Min Range: -1.1493
Max Act: 1.0879. Min Act: -0.1611
Data Index: 3220004 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1493. Min Range: -1.1493
Max Act: 1.0966. Min Act: -0.1613
Data Index: 4587630 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1493. Min Range: -1.1493
Max Act: 1.1054. Min Act: -0.1692
Data Index: 3205343 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1493. Min Range: -1.1493
Max Act: 1.1054. Min Act: -0.1688
Data Index: 3164592 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1493. Min Range: -1.1493
Max Act: 1.0966. Min Act: -0.1636
Data Index: 4040715 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1493. Min Range: -1.1493
Max Act: 1.0879. Min Act: -0.1700
Data Index: 7373949 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1493. Min Range: -1.1493
Max Act: 1.0879. Min Act: -0.1697
Data Index: 2771898 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1493. Min Range: -1.1493
Max Act: 1.0879. Min Act: -0.1694
Data Index: 560505 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19