Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3940 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.5667. Min Act: -0.0000

Data Index: 599908 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.5590. Min Act: -0.0000

Data Index: 963018 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4964. Min Act: -0.0000

Data Index: 452042 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4533. Min Act: -0.0000

Data Index: 437153 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4485. Min Act: -0.0000

Data Index: 992572 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4207. Min Act: -0.0000

Data Index: 799960 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4193. Min Act: -0.0000

Data Index: 1091672 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4311. Min Act: -0.0000

Data Index: 1299190 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4359. Min Act: -0.0000

Data Index: 1268962 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4255. Min Act: -0.0000

Data Index: 249612 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4109. Min Act: -0.0000

Data Index: 432212 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4081. Min Act: -0.0000

Data Index: 1157105 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4198. Min Act: -0.0000

Data Index: 1043314 (C4 (Web Text))

Max Activating Token Index: 407

Text #13

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4045. Min Act: -0.0000

Data Index: 96989 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.4024. Min Act: -0.0000

Data Index: 157874 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.3830. Min Act: -0.0000

Data Index: 324087 (C4 (Web Text))

Max Activating Token Index: 554

Text #16

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.3887. Min Act: -0.0000

Data Index: 925013 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.3898. Min Act: -0.0000

Data Index: 757597 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.3898. Min Act: -0.0000

Data Index: 718717 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.5667. Min Range: -0.5667

Max Act: 0.3859. Min Act: -0.0000

Data Index: 654260 (C4 (Web Text))

Max Activating Token Index: 775