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

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

Neuron 3053 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3328. Min Range: -3.3328

Max Act: 3.3328. Min Act: -0.0002

Data Index: 846808 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 3.3328. Min Range: -3.3328

Max Act: 2.9104. Min Act: -0.0002

Data Index: 632053 (C4 (Web Text))

Max Activating Token Index: 600

Text #2

Max Range: 3.3328. Min Range: -3.3328

Max Act: 3.1820. Min Act: -0.0001

Data Index: 453038 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 3.3328. Min Range: -3.3328

Max Act: 3.1560. Min Act: -0.0001

Data Index: 173447 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 3.3328. Min Range: -3.3328

Max Act: 2.9397. Min Act: -0.0002

Data Index: 559079 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 3.3328. Min Range: -3.3328

Max Act: 2.9869. Min Act: -0.0002

Data Index: 819648 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 3.3328. Min Range: -3.3328

Max Act: 2.7957. Min Act: -0.0001

Data Index: 118688 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 3.3328. Min Range: -3.3328

Max Act: 2.6163. Min Act: -0.0002

Data Index: 497638 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 3.3328. Min Range: -3.3328

Max Act: 2.6204. Min Act: -0.0001

Data Index: 418613 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 3.3328. Min Range: -3.3328

Max Act: 2.6636. Min Act: -0.0001

Data Index: 1190422 (C4 (Web Text))

Max Activating Token Index: 378

Text #10

Max Range: 3.3328. Min Range: -3.3328

Max Act: 2.6793. Min Act: -0.0002

Data Index: 570427 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 3.3328. Min Range: -3.3328

Max Act: 2.8223. Min Act: -0.0002

Data Index: 491604 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 3.3328. Min Range: -3.3328

Max Act: 2.6601. Min Act: -0.0002

Data Index: 558962 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 3.3328. Min Range: -3.3328

Max Act: 2.7533. Min Act: -0.0002

Data Index: 320679 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 3.3328. Min Range: -3.3328

Max Act: 2.7555. Min Act: -0.0001

Data Index: 18722 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 3.3328. Min Range: -3.3328

Max Act: 2.6225. Min Act: -0.0001

Data Index: 22977 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 3.3328. Min Range: -3.3328

Max Act: 2.4459. Min Act: -0.0002

Data Index: 539038 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 3.3328. Min Range: -3.3328

Max Act: 2.4369. Min Act: -0.0001

Data Index: 211835 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 3.3328. Min Range: -3.3328

Max Act: 2.3307. Min Act: -0.0002

Data Index: 1117152 (C4 (Web Text))

Max Activating Token Index: 709

Text #19

Max Range: 3.3328. Min Range: -3.3328

Max Act: 2.6931. Min Act: -0.0001

Data Index: 796507 (C4 (Web Text))

Max Activating Token Index: 369