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

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

Neuron 4389 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.8456. Min Act: -0.0000

Data Index: 348947 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.6144. Min Act: -0.0000

Data Index: 458473 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.4695. Min Act: -0.0000

Data Index: 457865 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.3661. Min Act: -0.0000

Data Index: 928632 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.2689. Min Act: -0.0000

Data Index: 221749 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.2815. Min Act: -0.0000

Data Index: 141826 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.2046. Min Act: -0.0000

Data Index: 67248 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.2893. Min Act: -0.0000

Data Index: 1189969 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.2645. Min Act: -0.0000

Data Index: 493857 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.2924. Min Act: -0.0000

Data Index: 584834 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.0977. Min Act: -0.0000

Data Index: 1016262 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.2367. Min Act: -0.0000

Data Index: 458503 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.2231. Min Act: -0.0000

Data Index: 175345 (C4 (Web Text))

Max Activating Token Index: 624

Text #13

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.2200. Min Act: -0.0000

Data Index: 755630 (C4 (Web Text))

Max Activating Token Index: 443

Text #14

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.2780. Min Act: -0.0000

Data Index: 391356 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.2352. Min Act: -0.0000

Data Index: 618265 (C4 (Web Text))

Max Activating Token Index: 547

Text #16

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.1967. Min Act: -0.0000

Data Index: 450109 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.1277. Min Act: -0.0000

Data Index: 264300 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.1209. Min Act: -0.0000

Data Index: 927453 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 1.8456. Min Range: -1.8456

Max Act: 1.1141. Min Act: -0.0000

Data Index: 319088 (C4 (Web Text))

Max Activating Token Index: 109