Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 994 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1068. Min Range: -1.1068

Max Act: 1.1068. Min Act: -0.0000

Data Index: 667634 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 1.1068. Min Range: -1.1068

Max Act: 1.0325. Min Act: -0.0001

Data Index: 535950 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.9502. Min Act: -0.0001

Data Index: 687500 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.8887. Min Act: -0.0000

Data Index: 288974 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.8886. Min Act: -0.0000

Data Index: 813852 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.8994. Min Act: -0.0001

Data Index: 1356195 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.8437. Min Act: -0.0000

Data Index: 682595 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.8198. Min Act: -0.0000

Data Index: 973453 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.8294. Min Act: -0.0000

Data Index: 1325925 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.7674. Min Act: -0.0000

Data Index: 690841 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.7216. Min Act: -0.0001

Data Index: 480608 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.7231. Min Act: -0.0000

Data Index: 12921 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.7143. Min Act: -0.0000

Data Index: 438227 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.7372. Min Act: -0.0001

Data Index: 1028837 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.7297. Min Act: -0.0001

Data Index: 1096096 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.7534. Min Act: -0.0000

Data Index: 925925 (C4 (Web Text))

Max Activating Token Index: 857

Text #16

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.7263. Min Act: -0.0001

Data Index: 1102456 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.7216. Min Act: -0.0001

Data Index: 332247 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.7164. Min Act: -0.0000

Data Index: 1345726 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 1.1068. Min Range: -1.1068

Max Act: 0.7366. Min Act: -0.0000

Data Index: 1322593 (C4 (Web Text))

Max Activating Token Index: 177