Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5999 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8788. Min Range: -1.8788

Max Act: 1.8498. Min Act: -0.0000

Data Index: 1287517 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 1.8788. Min Range: -1.8788

Max Act: 1.7950. Min Act: -0.0000

Data Index: 1570543 (Python Code)

Max Activating Token Index: 1004

Text #2

Max Range: 1.8788. Min Range: -1.8788

Max Act: 1.8788. Min Act: -0.0000

Data Index: 1551168 (Python Code)

Max Activating Token Index: 832

Text #3

Max Range: 1.8788. Min Range: -1.8788

Max Act: 1.7128. Min Act: -0.0000

Data Index: 384902 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 1.8788. Min Range: -1.8788

Max Act: 1.6645. Min Act: -0.0000

Data Index: 1158386 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 1.8788. Min Range: -1.8788

Max Act: 1.6670. Min Act: -0.0000

Data Index: 231722 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 1.8788. Min Range: -1.8788

Max Act: 1.6352. Min Act: -0.0000

Data Index: 1178086 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 1.8788. Min Range: -1.8788

Max Act: 1.5234. Min Act: -0.0000

Data Index: 822632 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 1.8788. Min Range: -1.8788

Max Act: 1.6241. Min Act: -0.0000

Data Index: 166324 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 1.8788. Min Range: -1.8788

Max Act: 1.6148. Min Act: -0.0000

Data Index: 247231 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 1.8788. Min Range: -1.8788

Max Act: 1.5725. Min Act: -0.0000

Data Index: 856087 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 1.8788. Min Range: -1.8788

Max Act: 1.6889. Min Act: -0.0000

Data Index: 38042 (C4 (Web Text))

Max Activating Token Index: 286

Text #12

Max Range: 1.8788. Min Range: -1.8788

Max Act: 1.5840. Min Act: -0.0000

Data Index: 402838 (C4 (Web Text))

Max Activating Token Index: 188

Text #13

Max Range: 1.8788. Min Range: -1.8788

Max Act: 1.5624. Min Act: -0.0000

Data Index: 1488615 (Python Code)

Max Activating Token Index: 420

Text #14

Max Range: 1.8788. Min Range: -1.8788

Max Act: 1.6100. Min Act: -0.0000

Data Index: 1107962 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 1.8788. Min Range: -1.8788

Max Act: 1.5160. Min Act: -0.0000

Data Index: 1394343 (Python Code)

Max Activating Token Index: 27

Text #16

Max Range: 1.8788. Min Range: -1.8788

Max Act: 1.5537. Min Act: -0.0000

Data Index: 919547 (C4 (Web Text))

Max Activating Token Index: 245

Text #17

Max Range: 1.8788. Min Range: -1.8788

Max Act: 1.5299. Min Act: -0.0000

Data Index: 196977 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 1.8788. Min Range: -1.8788

Max Act: 1.3682. Min Act: -0.0000

Data Index: 1034327 (C4 (Web Text))

Max Activating Token Index: 442

Text #19

Max Range: 1.8788. Min Range: -1.8788

Max Act: 1.4510. Min Act: -0.0000

Data Index: 300127 (C4 (Web Text))

Max Activating Token Index: 686