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

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

Neuron 1071 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2224. Min Range: -1.2224

Max Act: 1.2224. Min Act: -0.0000

Data Index: 138897 (C4 (Web Text))

Max Activating Token Index: 723

Text #1

Max Range: 1.2224. Min Range: -1.2224

Max Act: 0.8758. Min Act: -0.0000

Data Index: 1305176 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 1.2224. Min Range: -1.2224

Max Act: 0.9208. Min Act: -0.0000

Data Index: 848650 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 1.2224. Min Range: -1.2224

Max Act: 0.8957. Min Act: -0.0000

Data Index: 486925 (C4 (Web Text))

Max Activating Token Index: 925

Text #4

Max Range: 1.2224. Min Range: -1.2224

Max Act: 0.7993. Min Act: -0.0000

Data Index: 658729 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 1.2224. Min Range: -1.2224

Max Act: 0.7673. Min Act: -0.0000

Data Index: 1175666 (C4 (Web Text))

Max Activating Token Index: 974

Text #6

Max Range: 1.2224. Min Range: -1.2224

Max Act: 0.8240. Min Act: -0.0000

Data Index: 798356 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 1.2224. Min Range: -1.2224

Max Act: 0.8154. Min Act: -0.0000

Data Index: 1307698 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 1.2224. Min Range: -1.2224

Max Act: 0.7685. Min Act: -0.0000

Data Index: 328228 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 1.2224. Min Range: -1.2224

Max Act: 0.7796. Min Act: -0.0000

Data Index: 111583 (C4 (Web Text))

Max Activating Token Index: 933

Text #10

Max Range: 1.2224. Min Range: -1.2224

Max Act: 0.7503. Min Act: -0.0000

Data Index: 109278 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 1.2224. Min Range: -1.2224

Max Act: 0.8185. Min Act: -0.0000

Data Index: 71688 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 1.2224. Min Range: -1.2224

Max Act: 0.7170. Min Act: -0.0000

Data Index: 402130 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 1.2224. Min Range: -1.2224

Max Act: 0.7621. Min Act: -0.0000

Data Index: 629397 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 1.2224. Min Range: -1.2224

Max Act: 0.7350. Min Act: -0.0000

Data Index: 754166 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 1.2224. Min Range: -1.2224

Max Act: 0.5984. Min Act: -0.0000

Data Index: 546678 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 1.2224. Min Range: -1.2224

Max Act: 0.6568. Min Act: -0.0000

Data Index: 224373 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 1.2224. Min Range: -1.2224

Max Act: 0.6627. Min Act: -0.0000

Data Index: 572377 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 1.2224. Min Range: -1.2224

Max Act: 0.6392. Min Act: -0.0000

Data Index: 124424 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 1.2224. Min Range: -1.2224

Max Act: 0.6612. Min Act: -0.0000

Data Index: 162450 (C4 (Web Text))

Max Activating Token Index: 568