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

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

Neuron 3267 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3801. Min Range: -5.3801

Max Act: 5.3801. Min Act: -0.0000

Data Index: 297494 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 5.3801. Min Range: -5.3801

Max Act: 5.3007. Min Act: -0.0000

Data Index: 154294 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 5.3801. Min Range: -5.3801

Max Act: 4.6467. Min Act: -0.0000

Data Index: 1043396 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 5.3801. Min Range: -5.3801

Max Act: 4.4362. Min Act: -0.0000

Data Index: 444727 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 5.3801. Min Range: -5.3801

Max Act: 3.8119. Min Act: -0.0000

Data Index: 1032686 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 5.3801. Min Range: -5.3801

Max Act: 4.0960. Min Act: -0.0000

Data Index: 416180 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 5.3801. Min Range: -5.3801

Max Act: 3.7865. Min Act: -0.0000

Data Index: 1155242 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 5.3801. Min Range: -5.3801

Max Act: 3.4425. Min Act: -0.0000

Data Index: 416778 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 5.3801. Min Range: -5.3801

Max Act: 3.2413. Min Act: -0.0000

Data Index: 113701 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 5.3801. Min Range: -5.3801

Max Act: 3.3087. Min Act: -0.0000

Data Index: 515880 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 5.3801. Min Range: -5.3801

Max Act: 3.3070. Min Act: -0.0000

Data Index: 562108 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 5.3801. Min Range: -5.3801

Max Act: 2.8930. Min Act: -0.0000

Data Index: 343796 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 5.3801. Min Range: -5.3801

Max Act: 3.2647. Min Act: -0.0000

Data Index: 833750 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 5.3801. Min Range: -5.3801

Max Act: 2.9425. Min Act: -0.0000

Data Index: 17700 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 5.3801. Min Range: -5.3801

Max Act: 3.0586. Min Act: -0.0000

Data Index: 958438 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 5.3801. Min Range: -5.3801

Max Act: 2.7174. Min Act: -0.0000

Data Index: 198265 (C4 (Web Text))

Max Activating Token Index: 273

Text #16

Max Range: 5.3801. Min Range: -5.3801

Max Act: 3.1298. Min Act: -0.0000

Data Index: 441027 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 5.3801. Min Range: -5.3801

Max Act: 3.0623. Min Act: -0.0000

Data Index: 1270000 (C4 (Web Text))

Max Activating Token Index: 205

Text #18

Max Range: 5.3801. Min Range: -5.3801

Max Act: 2.8109. Min Act: -0.0000

Data Index: 998360 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 5.3801. Min Range: -5.3801

Max Act: 2.8897. Min Act: -0.0000

Data Index: 22235 (C4 (Web Text))

Max Activating Token Index: 24