Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1372 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.4029. Min Act: -0.0003

Data Index: 267383 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.4204. Min Act: -0.0003

Data Index: 1193946 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3749. Min Act: -0.0003

Data Index: 316312 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3677. Min Act: -0.0003

Data Index: 672667 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3764. Min Act: -0.0003

Data Index: 1321231 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3888. Min Act: -0.0003

Data Index: 462924 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3993. Min Act: -0.0003

Data Index: 1312323 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3727. Min Act: -0.0003

Data Index: 1286731 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3829. Min Act: -0.0003

Data Index: 1102886 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3513. Min Act: -0.0003

Data Index: 1154903 (C4 (Web Text))

Max Activating Token Index: 79

Text #10

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3242. Min Act: -0.0003

Data Index: 1206013 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3673. Min Act: -0.0003

Data Index: 147902 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3860. Min Act: -0.0003

Data Index: 338042 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3456. Min Act: -0.0003

Data Index: 131688 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3395. Min Act: -0.0003

Data Index: 815566 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3294. Min Act: -0.0003

Data Index: 990713 (C4 (Web Text))

Max Activating Token Index: 380

Text #16

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3408. Min Act: -0.0003

Data Index: 172220 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3127. Min Act: -0.0003

Data Index: 681684 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3138. Min Act: -0.0003

Data Index: 1091821 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3587. Min Act: -0.0003

Data Index: 869849 (C4 (Web Text))

Max Activating Token Index: 784