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

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

Neuron 1144 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.8425. Min Act: -0.0001

Data Index: 876616 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.5534. Min Act: -0.0001

Data Index: 1055699 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.5616. Min Act: -0.0001

Data Index: 220653 (C4 (Web Text))

Max Activating Token Index: 575

Text #3

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.5687. Min Act: -0.0000

Data Index: 899987 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.5196. Min Act: -0.0001

Data Index: 1111389 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.5521. Min Act: -0.0000

Data Index: 1069309 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.5176. Min Act: -0.0000

Data Index: 838683 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.5073. Min Act: -0.0001

Data Index: 1005889 (C4 (Web Text))

Max Activating Token Index: 597

Text #8

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.6330. Min Act: -0.0000

Data Index: 489879 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.5063. Min Act: -0.0001

Data Index: 1189174 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.4962. Min Act: -0.0001

Data Index: 559258 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.4801. Min Act: -0.0001

Data Index: 951886 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.4607. Min Act: -0.0000

Data Index: 1051969 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.4795. Min Act: -0.0000

Data Index: 60375 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.4659. Min Act: -0.0001

Data Index: 847577 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.4183. Min Act: -0.0001

Data Index: 421747 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.4652. Min Act: -0.0001

Data Index: 1004700 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.4542. Min Act: -0.0001

Data Index: 1334971 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.4345. Min Act: -0.0001

Data Index: 1028318 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.8425. Min Range: -0.8425

Max Act: 0.4006. Min Act: -0.0001

Data Index: 990610 (C4 (Web Text))

Max Activating Token Index: 311