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

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

Neuron 2054 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1421. Min Act: -0.0000

Data Index: 1306423 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1445. Min Act: -0.0000

Data Index: 669178 (C4 (Web Text))

Max Activating Token Index: 141

Text #2

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1363. Min Act: -0.0001

Data Index: 1013164 (C4 (Web Text))

Max Activating Token Index: 872

Text #3

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1327. Min Act: -0.0000

Data Index: 246515 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1334. Min Act: -0.0000

Data Index: 1095794 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1318. Min Act: -0.0000

Data Index: 167135 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1264. Min Act: -0.0000

Data Index: 229872 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1149. Min Act: -0.0000

Data Index: 706632 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1235. Min Act: -0.0000

Data Index: 258424 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1033. Min Act: -0.0000

Data Index: 8750 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1019. Min Act: -0.0000

Data Index: 1257907 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0960. Min Act: -0.0000

Data Index: 315378 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0871. Min Act: -0.0000

Data Index: 374103 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1002. Min Act: -0.0000

Data Index: 949634 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0953. Min Act: -0.0000

Data Index: 264120 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0932. Min Act: -0.0000

Data Index: 785988 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0860. Min Act: -0.0001

Data Index: 454293 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0823. Min Act: -0.0000

Data Index: 622269 (C4 (Web Text))

Max Activating Token Index: 773

Text #18

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0892. Min Act: -0.0000

Data Index: 211345 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.0868. Min Act: -0.0000

Data Index: 477583 (C4 (Web Text))

Max Activating Token Index: 327