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

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

Neuron 2100 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: 1.0763. Min Range: -1.0763

Max Act: 1.0763. Min Act: -0.0000

Data Index: 257908 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.7096. Min Act: -0.0000

Data Index: 1272435 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.6481. Min Act: -0.0000

Data Index: 444544 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.5247. Min Act: -0.0000

Data Index: 491046 (C4 (Web Text))

Max Activating Token Index: 390

Text #4

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.5195. Min Act: -0.0000

Data Index: 345222 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.4870. Min Act: -0.0000

Data Index: 588678 (C4 (Web Text))

Max Activating Token Index: 608

Text #6

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.5403. Min Act: -0.0000

Data Index: 256933 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.5365. Min Act: -0.0000

Data Index: 1210656 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.5065. Min Act: -0.0000

Data Index: 249788 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.5077. Min Act: -0.0000

Data Index: 1177212 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.4823. Min Act: -0.0000

Data Index: 510620 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.5063. Min Act: -0.0000

Data Index: 484003 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.4802. Min Act: -0.0000

Data Index: 742235 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.4863. Min Act: -0.0000

Data Index: 516652 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.4699. Min Act: -0.0000

Data Index: 368831 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.4421. Min Act: -0.0000

Data Index: 1161927 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.4401. Min Act: -0.0000

Data Index: 1233888 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.4500. Min Act: -0.0000

Data Index: 1030190 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.4671. Min Act: -0.0000

Data Index: 646812 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 1.0763. Min Range: -1.0763

Max Act: 0.4090. Min Act: -0.0000

Data Index: 715892 (C4 (Web Text))

Max Activating Token Index: 855