Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2522 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3672. Min Range: -6.3672
Max Act: 6.3359. Min Act: -0.1700
Data Index: 5877076 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3672. Min Range: -6.3672
Max Act: 6.3359. Min Act: -0.1700
Data Index: 2356110 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3672. Min Range: -6.3672
Max Act: 6.3672. Min Act: -0.1700
Data Index: 2356109 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3672. Min Range: -6.3672
Max Act: 6.1797. Min Act: -0.1700
Data Index: 6863511 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3672. Min Range: -6.3672
Max Act: 6.1484. Min Act: -0.1700
Data Index: 7720440 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3672. Min Range: -6.3672
Max Act: 6.0859. Min Act: -0.1700
Data Index: 6363796 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3672. Min Range: -6.3672
Max Act: 6.0547. Min Act: -0.1700
Data Index: 7293973 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3672. Min Range: -6.3672
Max Act: 6.0547. Min Act: -0.1700
Data Index: 1297351 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3672. Min Range: -6.3672
Max Act: 6.0547. Min Act: -0.1700
Data Index: 2148231 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3672. Min Range: -6.3672
Max Act: 6.0859. Min Act: -0.1700
Data Index: 6345100 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3672. Min Range: -6.3672
Max Act: 5.9922. Min Act: -0.1700
Data Index: 6517673 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3672. Min Range: -6.3672
Max Act: 6.0234. Min Act: -0.1700
Data Index: 835789 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3672. Min Range: -6.3672
Max Act: 5.9609. Min Act: -0.1700
Data Index: 7720439 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3672. Min Range: -6.3672
Max Act: 5.9297. Min Act: -0.1700
Data Index: 2356104 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3672. Min Range: -6.3672
Max Act: 5.9609. Min Act: -0.1700
Data Index: 5908550 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3672. Min Range: -6.3672
Max Act: 5.8672. Min Act: -0.1700
Data Index: 3298780 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3672. Min Range: -6.3672
Max Act: 5.8984. Min Act: -0.1700
Data Index: 2305334 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3672. Min Range: -6.3672
Max Act: 5.9609. Min Act: -0.1700
Data Index: 4452217 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3672. Min Range: -6.3672
Max Act: 5.8672. Min Act: -0.1700
Data Index: 2269059 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3672. Min Range: -6.3672
Max Act: 5.8672. Min Act: -0.1700
Data Index: 1022164 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19