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

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

Neuron 1522 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4988. Min Range: -0.4988

Max Act: 0.4627. Min Act: -0.0001

Data Index: 1123179 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 0.4988. Min Range: -0.4988

Max Act: 0.4988. Min Act: -0.0000

Data Index: 153168 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 0.4988. Min Range: -0.4988

Max Act: 0.4659. Min Act: -0.0000

Data Index: 795683 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 0.4988. Min Range: -0.4988

Max Act: 0.4468. Min Act: -0.0000

Data Index: 878985 (C4 (Web Text))

Max Activating Token Index: 399

Text #4

Max Range: 0.4988. Min Range: -0.4988

Max Act: 0.4438. Min Act: -0.0001

Data Index: 469310 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 0.4988. Min Range: -0.4988

Max Act: 0.4131. Min Act: -0.0001

Data Index: 1313102 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 0.4988. Min Range: -0.4988

Max Act: 0.4287. Min Act: -0.0001

Data Index: 445351 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.4988. Min Range: -0.4988

Max Act: 0.4438. Min Act: -0.0000

Data Index: 574538 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 0.4988. Min Range: -0.4988

Max Act: 0.3841. Min Act: -0.0000

Data Index: 431578 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 0.4988. Min Range: -0.4988

Max Act: 0.4103. Min Act: -0.0000

Data Index: 85078 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 0.4988. Min Range: -0.4988

Max Act: 0.4421. Min Act: -0.0000

Data Index: 347267 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 0.4988. Min Range: -0.4988

Max Act: 0.4099. Min Act: -0.0000

Data Index: 571225 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 0.4988. Min Range: -0.4988

Max Act: 0.4181. Min Act: -0.0000

Data Index: 98084 (C4 (Web Text))

Max Activating Token Index: 159

Text #13

Max Range: 0.4988. Min Range: -0.4988

Max Act: 0.4348. Min Act: -0.0000

Data Index: 317934 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 0.4988. Min Range: -0.4988

Max Act: 0.4189. Min Act: -0.0000

Data Index: 71353 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 0.4988. Min Range: -0.4988

Max Act: 0.4271. Min Act: -0.0001

Data Index: 545881 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 0.4988. Min Range: -0.4988

Max Act: 0.4140. Min Act: -0.0001

Data Index: 435507 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 0.4988. Min Range: -0.4988

Max Act: 0.4101. Min Act: -0.0000

Data Index: 722859 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.4988. Min Range: -0.4988

Max Act: 0.4066. Min Act: -0.0000

Data Index: 1022128 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 0.4988. Min Range: -0.4988

Max Act: 0.4064. Min Act: -0.0001

Data Index: 400243 (C4 (Web Text))

Max Activating Token Index: 31