Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3449 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8583. Min Range: -1.8583

Max Act: 1.7859. Min Act: -0.0001

Data Index: 448718 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 1.8583. Min Range: -1.8583

Max Act: 1.8583. Min Act: -0.0001

Data Index: 912068 (C4 (Web Text))

Max Activating Token Index: 938

Text #2

Max Range: 1.8583. Min Range: -1.8583

Max Act: 1.6307. Min Act: -0.0001

Data Index: 719364 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 1.8583. Min Range: -1.8583

Max Act: 1.8109. Min Act: -0.0001

Data Index: 611150 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 1.8583. Min Range: -1.8583

Max Act: 1.6336. Min Act: -0.0001

Data Index: 148369 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 1.8583. Min Range: -1.8583

Max Act: 1.5225. Min Act: -0.0001

Data Index: 1153825 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 1.8583. Min Range: -1.8583

Max Act: 1.5487. Min Act: -0.0001

Data Index: 805535 (C4 (Web Text))

Max Activating Token Index: 372

Text #7

Max Range: 1.8583. Min Range: -1.8583

Max Act: 1.4926. Min Act: -0.0001

Data Index: 326146 (C4 (Web Text))

Max Activating Token Index: 598

Text #8

Max Range: 1.8583. Min Range: -1.8583

Max Act: 1.2391. Min Act: -0.0001

Data Index: 451967 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 1.8583. Min Range: -1.8583

Max Act: 1.3050. Min Act: -0.0001

Data Index: 410542 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 1.8583. Min Range: -1.8583

Max Act: 1.3077. Min Act: -0.0001

Data Index: 557306 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 1.8583. Min Range: -1.8583

Max Act: 1.1801. Min Act: -0.0001

Data Index: 783159 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 1.8583. Min Range: -1.8583

Max Act: 1.1915. Min Act: -0.0001

Data Index: 444988 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 1.8583. Min Range: -1.8583

Max Act: 1.1776. Min Act: -0.0001

Data Index: 1206650 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 1.8583. Min Range: -1.8583

Max Act: 1.1279. Min Act: -0.0001

Data Index: 303655 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 1.8583. Min Range: -1.8583

Max Act: 1.1232. Min Act: -0.0001

Data Index: 327526 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 1.8583. Min Range: -1.8583

Max Act: 1.1512. Min Act: -0.0001

Data Index: 1008035 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 1.8583. Min Range: -1.8583

Max Act: 1.0654. Min Act: -0.0001

Data Index: 993592 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 1.8583. Min Range: -1.8583

Max Act: 1.0412. Min Act: -0.0001

Data Index: 742999 (C4 (Web Text))

Max Activating Token Index: 278

Text #19

Max Range: 1.8583. Min Range: -1.8583

Max Act: 1.1269. Min Act: -0.0001

Data Index: 698220 (C4 (Web Text))

Max Activating Token Index: 15