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

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

Neuron 1264 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: 1.1566. Min Range: -1.1566

Max Act: 1.1566. Min Act: -0.0000

Data Index: 270642 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 1.1566. Min Range: -1.1566

Max Act: 1.0429. Min Act: -0.0000

Data Index: 984994 (C4 (Web Text))

Max Activating Token Index: 473

Text #2

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.9119. Min Act: -0.0000

Data Index: 590719 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.8650. Min Act: -0.0000

Data Index: 1349892 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.9549. Min Act: -0.0000

Data Index: 28613 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.8944. Min Act: -0.0000

Data Index: 453782 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.8809. Min Act: -0.0000

Data Index: 1001026 (C4 (Web Text))

Max Activating Token Index: 425

Text #7

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.8898. Min Act: -0.0000

Data Index: 1145967 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.8055. Min Act: -0.0000

Data Index: 904464 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.8554. Min Act: -0.0000

Data Index: 907148 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.8559. Min Act: -0.0000

Data Index: 1155172 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.8411. Min Act: -0.0000

Data Index: 486736 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.8245. Min Act: -0.0000

Data Index: 757069 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.8481. Min Act: -0.0000

Data Index: 919934 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.8238. Min Act: -0.0000

Data Index: 1070340 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.7638. Min Act: -0.0000

Data Index: 1070147 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.7959. Min Act: -0.0000

Data Index: 55006 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.7765. Min Act: -0.0000

Data Index: 1226704 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.7848. Min Act: -0.0000

Data Index: 1034881 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 1.1566. Min Range: -1.1566

Max Act: 0.7887. Min Act: -0.0000

Data Index: 409029 (C4 (Web Text))

Max Activating Token Index: 957