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

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

Neuron 2898 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7393. Min Range: -2.7393

Max Act: 2.7393. Min Act: -0.0000

Data Index: 121222 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 2.7393. Min Range: -2.7393

Max Act: 2.5426. Min Act: -0.0000

Data Index: 999448 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 2.7393. Min Range: -2.7393

Max Act: 2.7038. Min Act: -0.0000

Data Index: 1281506 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 2.7393. Min Range: -2.7393

Max Act: 2.1259. Min Act: -0.0000

Data Index: 505982 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 2.7393. Min Range: -2.7393

Max Act: 2.1872. Min Act: -0.0000

Data Index: 993358 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 2.7393. Min Range: -2.7393

Max Act: 1.8957. Min Act: -0.0000

Data Index: 1121869 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 2.7393. Min Range: -2.7393

Max Act: 2.0448. Min Act: -0.0000

Data Index: 848980 (C4 (Web Text))

Max Activating Token Index: 944

Text #7

Max Range: 2.7393. Min Range: -2.7393

Max Act: 2.0574. Min Act: -0.0000

Data Index: 516224 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 2.7393. Min Range: -2.7393

Max Act: 2.0099. Min Act: -0.0000

Data Index: 916651 (C4 (Web Text))

Max Activating Token Index: 136

Text #9

Max Range: 2.7393. Min Range: -2.7393

Max Act: 1.8630. Min Act: -0.0000

Data Index: 169354 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 2.7393. Min Range: -2.7393

Max Act: 2.0759. Min Act: -0.0000

Data Index: 790417 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 2.7393. Min Range: -2.7393

Max Act: 1.8521. Min Act: -0.0000

Data Index: 1261162 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 2.7393. Min Range: -2.7393

Max Act: 1.8476. Min Act: -0.0001

Data Index: 494601 (C4 (Web Text))

Max Activating Token Index: 194

Text #13

Max Range: 2.7393. Min Range: -2.7393

Max Act: 1.7635. Min Act: -0.0000

Data Index: 1105954 (C4 (Web Text))

Max Activating Token Index: 515

Text #14

Max Range: 2.7393. Min Range: -2.7393

Max Act: 1.9511. Min Act: -0.0000

Data Index: 274856 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 2.7393. Min Range: -2.7393

Max Act: 1.8289. Min Act: -0.0000

Data Index: 600470 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 2.7393. Min Range: -2.7393

Max Act: 1.7965. Min Act: -0.0000

Data Index: 1154625 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 2.7393. Min Range: -2.7393

Max Act: 1.5903. Min Act: -0.0000

Data Index: 848985 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 2.7393. Min Range: -2.7393

Max Act: 1.6269. Min Act: -0.0000

Data Index: 509565 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 2.7393. Min Range: -2.7393

Max Act: 1.7441. Min Act: -0.0000

Data Index: 310266 (C4 (Web Text))

Max Activating Token Index: 280