Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1121 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6054. Min Range: -6.6054
Max Act: 6.6054. Min Act: -0.1700
Data Index: 2388255 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6054. Min Range: -6.6054
Max Act: 6.3867. Min Act: -0.1700
Data Index: 1199296 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6054. Min Range: -6.6054
Max Act: 6.2304. Min Act: -0.1700
Data Index: 2840644 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6054. Min Range: -6.6054
Max Act: 6.1992. Min Act: -0.1700
Data Index: 8680277 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6054. Min Range: -6.6054
Max Act: 6.1367. Min Act: -0.1700
Data Index: 2388256 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6054. Min Range: -6.6054
Max Act: 6.0429. Min Act: -0.1700
Data Index: 8144541 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6054. Min Range: -6.6054
Max Act: 6.0117. Min Act: -0.1700
Data Index: 3578684 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6054. Min Range: -6.6054
Max Act: 6.0429. Min Act: -0.1700
Data Index: 601831 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6054. Min Range: -6.6054
Max Act: 5.9179. Min Act: -0.1700
Data Index: 3956445 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6054. Min Range: -6.6054
Max Act: 5.9179. Min Act: -0.1700
Data Index: 1362835 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6054. Min Range: -6.6054
Max Act: 5.8242. Min Act: -0.1700
Data Index: 3055220 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6054. Min Range: -6.6054
Max Act: 5.7929. Min Act: -0.1700
Data Index: 3490922 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6054. Min Range: -6.6054
Max Act: 5.8554. Min Act: -0.1700
Data Index: 490582 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6054. Min Range: -6.6054
Max Act: 5.7929. Min Act: -0.1700
Data Index: 6866558 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6054. Min Range: -6.6054
Max Act: 5.8242. Min Act: -0.1700
Data Index: 5038093 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6054. Min Range: -6.6054
Max Act: 5.8242. Min Act: -0.1700
Data Index: 8073791 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6054. Min Range: -6.6054
Max Act: 5.7929. Min Act: -0.1700
Data Index: 7270923 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6054. Min Range: -6.6054
Max Act: 5.8554. Min Act: -0.1700
Data Index: 1662139 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6054. Min Range: -6.6054
Max Act: 5.7617. Min Act: -0.1700
Data Index: 2034422 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6054. Min Range: -6.6054
Max Act: 5.7617. Min Act: -0.1700
Data Index: 5531367 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #19