Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2943 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.1042. Min Range: -3.1042

Max Act: 3.1042. Min Act: -0.0000

Data Index: 677462 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.9212. Min Act: -0.0000

Data Index: 454033 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.6994. Min Act: -0.0000

Data Index: 874572 (C4 (Web Text))

Max Activating Token Index: 1018

Text #3

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.7119. Min Act: -0.0000

Data Index: 577772 (C4 (Web Text))

Max Activating Token Index: 120

Text #4

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.7362. Min Act: -0.0000

Data Index: 1322405 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.7074. Min Act: -0.0000

Data Index: 582599 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.5629. Min Act: -0.0000

Data Index: 811351 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.6653. Min Act: -0.0000

Data Index: 1118200 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.6246. Min Act: -0.0000

Data Index: 1128654 (C4 (Web Text))

Max Activating Token Index: 98

Text #9

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.5031. Min Act: -0.0000

Data Index: 290770 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.4901. Min Act: -0.0000

Data Index: 1328966 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.5225. Min Act: -0.0000

Data Index: 567954 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.5270. Min Act: -0.0000

Data Index: 194092 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.6532. Min Act: -0.0000

Data Index: 965816 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.5111. Min Act: -0.0000

Data Index: 567192 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.3221. Min Act: -0.0000

Data Index: 364302 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.4498. Min Act: -0.0000

Data Index: 409387 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.4494. Min Act: -0.0000

Data Index: 406908 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.4230. Min Act: -0.0000

Data Index: 1293429 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 3.1042. Min Range: -3.1042

Max Act: 2.4299. Min Act: -0.0000

Data Index: 1273797 (C4 (Web Text))

Max Activating Token Index: 951