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

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

Neuron 2934 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: 0.4847. Min Range: -0.4847

Max Act: 0.4847. Min Act: -0.0000

Data Index: 711415 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4377. Min Act: -0.0000

Data Index: 276663 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3914. Min Act: -0.0000

Data Index: 1287458 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3833. Min Act: -0.0000

Data Index: 1135686 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3969. Min Act: -0.0000

Data Index: 809000 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3533. Min Act: -0.0000

Data Index: 151226 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3545. Min Act: -0.0000

Data Index: 96228 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3401. Min Act: -0.0000

Data Index: 962661 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3402. Min Act: -0.0000

Data Index: 575221 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3602. Min Act: -0.0000

Data Index: 708015 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3464. Min Act: -0.0000

Data Index: 315148 (C4 (Web Text))

Max Activating Token Index: 653

Text #11

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3368. Min Act: -0.0000

Data Index: 294438 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3603. Min Act: -0.0000

Data Index: 1163247 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3238. Min Act: -0.0000

Data Index: 686472 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3412. Min Act: -0.0000

Data Index: 745998 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3308. Min Act: -0.0000

Data Index: 204885 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3136. Min Act: -0.0000

Data Index: 1225025 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3064. Min Act: -0.0000

Data Index: 860487 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3186. Min Act: -0.0000

Data Index: 393731 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3352. Min Act: -0.0000

Data Index: 1158195 (C4 (Web Text))

Max Activating Token Index: 662