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

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

Neuron 1712 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: 2.5815. Min Range: -2.5815

Max Act: 2.5815. Min Act: -0.0000

Data Index: 1317871 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 2.5815. Min Range: -2.5815

Max Act: 2.2208. Min Act: -0.0000

Data Index: 777765 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 2.5815. Min Range: -2.5815

Max Act: 2.2262. Min Act: -0.0000

Data Index: 506864 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 2.5815. Min Range: -2.5815

Max Act: 2.0228. Min Act: -0.0000

Data Index: 303509 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 2.5815. Min Range: -2.5815

Max Act: 2.0171. Min Act: -0.0000

Data Index: 554111 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 2.5815. Min Range: -2.5815

Max Act: 1.9405. Min Act: -0.0000

Data Index: 1047424 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 2.5815. Min Range: -2.5815

Max Act: 2.1105. Min Act: -0.0000

Data Index: 1074346 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 2.5815. Min Range: -2.5815

Max Act: 2.0156. Min Act: -0.0000

Data Index: 475462 (C4 (Web Text))

Max Activating Token Index: 729

Text #8

Max Range: 2.5815. Min Range: -2.5815

Max Act: 1.9846. Min Act: -0.0000

Data Index: 686515 (C4 (Web Text))

Max Activating Token Index: 666

Text #9

Max Range: 2.5815. Min Range: -2.5815

Max Act: 1.8587. Min Act: -0.0000

Data Index: 50515 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 2.5815. Min Range: -2.5815

Max Act: 1.8612. Min Act: -0.0000

Data Index: 312596 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 2.5815. Min Range: -2.5815

Max Act: 1.9586. Min Act: -0.0000

Data Index: 288045 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 2.5815. Min Range: -2.5815

Max Act: 1.9222. Min Act: -0.0000

Data Index: 202739 (C4 (Web Text))

Max Activating Token Index: 541

Text #13

Max Range: 2.5815. Min Range: -2.5815

Max Act: 1.7975. Min Act: -0.0000

Data Index: 1289409 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 2.5815. Min Range: -2.5815

Max Act: 2.0189. Min Act: -0.0000

Data Index: 680342 (C4 (Web Text))

Max Activating Token Index: 991

Text #15

Max Range: 2.5815. Min Range: -2.5815

Max Act: 2.1292. Min Act: -0.0000

Data Index: 1178485 (C4 (Web Text))

Max Activating Token Index: 630

Text #16

Max Range: 2.5815. Min Range: -2.5815

Max Act: 1.7981. Min Act: -0.0000

Data Index: 417714 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 2.5815. Min Range: -2.5815

Max Act: 1.8701. Min Act: -0.0000

Data Index: 1046407 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 2.5815. Min Range: -2.5815

Max Act: 1.8427. Min Act: -0.0000

Data Index: 983125 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 2.5815. Min Range: -2.5815

Max Act: 2.0504. Min Act: -0.0000

Data Index: 1031209 (C4 (Web Text))

Max Activating Token Index: 713