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

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

Neuron 3470 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: 1.1072. Min Range: -1.1072

Max Act: 1.1072. Min Act: -0.0000

Data Index: 770922 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.9719. Min Act: -0.0000

Data Index: 118998 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 1.1072. Min Range: -1.1072

Max Act: 1.0909. Min Act: -0.0000

Data Index: 876129 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.9343. Min Act: -0.0000

Data Index: 941064 (C4 (Web Text))

Max Activating Token Index: 657

Text #4

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.9252. Min Act: -0.0000

Data Index: 597097 (C4 (Web Text))

Max Activating Token Index: 135

Text #5

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.8480. Min Act: -0.0000

Data Index: 993421 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.7958. Min Act: -0.0000

Data Index: 1041721 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.8408. Min Act: -0.0000

Data Index: 577252 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.7331. Min Act: -0.0000

Data Index: 1134048 (C4 (Web Text))

Max Activating Token Index: 732

Text #9

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.6823. Min Act: -0.0000

Data Index: 851469 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.7038. Min Act: -0.0000

Data Index: 913141 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.6983. Min Act: -0.0000

Data Index: 1334642 (C4 (Web Text))

Max Activating Token Index: 514

Text #12

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.7442. Min Act: -0.0000

Data Index: 73271 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.6961. Min Act: -0.0000

Data Index: 832058 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.6413. Min Act: -0.0000

Data Index: 1152125 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.6508. Min Act: -0.0000

Data Index: 839455 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.6691. Min Act: -0.0000

Data Index: 889190 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.6621. Min Act: -0.0000

Data Index: 179494 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.6540. Min Act: -0.0000

Data Index: 1118283 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.6796. Min Act: -0.0000

Data Index: 1097359 (C4 (Web Text))

Max Activating Token Index: 660