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

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

Neuron 35 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.8808. Min Act: -0.0000

Data Index: 28532 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.8101. Min Act: -0.0000

Data Index: 801858 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.8089. Min Act: -0.0000

Data Index: 559101 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.8038. Min Act: -0.0000

Data Index: 763042 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.7756. Min Act: -0.0000

Data Index: 568461 (C4 (Web Text))

Max Activating Token Index: 1022

Text #5

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.7398. Min Act: -0.0000

Data Index: 1000468 (C4 (Web Text))

Max Activating Token Index: 773

Text #6

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.7309. Min Act: -0.0000

Data Index: 488464 (C4 (Web Text))

Max Activating Token Index: 286

Text #7

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.7239. Min Act: -0.0000

Data Index: 313813 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.7731. Min Act: -0.0000

Data Index: 119762 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.7651. Min Act: -0.0000

Data Index: 760274 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.7438. Min Act: -0.0000

Data Index: 289376 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.7033. Min Act: -0.0000

Data Index: 13394 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.7181. Min Act: -0.0000

Data Index: 454114 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6989. Min Act: -0.0000

Data Index: 187381 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6546. Min Act: -0.0000

Data Index: 1203597 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6973. Min Act: -0.0000

Data Index: 1132395 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1102878 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6903. Min Act: -0.0000

Data Index: 1023244 (C4 (Web Text))

Max Activating Token Index: 934

Text #18

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6729. Min Act: -0.0000

Data Index: 1290703 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 0.8808. Min Range: -0.8808

Max Act: 0.6726. Min Act: -0.0000

Data Index: 764648 (C4 (Web Text))

Max Activating Token Index: 46