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

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

Neuron 3436 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: 0.3331. Min Range: -0.3331

Max Act: 0.3331. Min Act: -0.0000

Data Index: 885804 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2720. Min Act: -0.0000

Data Index: 777017 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2754. Min Act: -0.0000

Data Index: 473982 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2424. Min Act: -0.0000

Data Index: 1221773 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2592. Min Act: -0.0000

Data Index: 226123 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2472. Min Act: -0.0000

Data Index: 840674 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2390. Min Act: -0.0000

Data Index: 1336685 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2659. Min Act: -0.0000

Data Index: 732229 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2394. Min Act: -0.0000

Data Index: 22613 (C4 (Web Text))

Max Activating Token Index: 33

Text #9

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2343. Min Act: -0.0000

Data Index: 1338806 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2198. Min Act: -0.0000

Data Index: 758056 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2109. Min Act: -0.0000

Data Index: 333305 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2097. Min Act: -0.0000

Data Index: 596040 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2107. Min Act: -0.0000

Data Index: 786459 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2161. Min Act: -0.0000

Data Index: 1290492 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2093. Min Act: -0.0000

Data Index: 331303 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.1930. Min Act: -0.0000

Data Index: 1159493 (C4 (Web Text))

Max Activating Token Index: 733

Text #17

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2122. Min Act: -0.0000

Data Index: 992957 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2179. Min Act: -0.0000

Data Index: 736151 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 0.3331. Min Range: -0.3331

Max Act: 0.2090. Min Act: -0.0000

Data Index: 667676 (C4 (Web Text))

Max Activating Token Index: 137