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

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

Neuron 2095 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0568. Min Act: -0.0002

Data Index: 675640 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0501. Min Act: -0.0002

Data Index: 510967 (C4 (Web Text))

Max Activating Token Index: 995

Text #2

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0446. Min Act: -0.0002

Data Index: 567038 (C4 (Web Text))

Max Activating Token Index: 678

Text #3

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0485. Min Act: -0.0002

Data Index: 541915 (C4 (Web Text))

Max Activating Token Index: 907

Text #4

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0452. Min Act: -0.0002

Data Index: 1044237 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0471. Min Act: -0.0002

Data Index: 109003 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0466. Min Act: -0.0002

Data Index: 25101 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0463. Min Act: -0.0002

Data Index: 31151 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1121061 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0459. Min Act: -0.0002

Data Index: 963703 (C4 (Web Text))

Max Activating Token Index: 998

Text #10

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0442. Min Act: -0.0002

Data Index: 591238 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0419. Min Act: -0.0002

Data Index: 1308370 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0408. Min Act: -0.0002

Data Index: 683042 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0449. Min Act: -0.0002

Data Index: 165395 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1238594 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0425. Min Act: -0.0002

Data Index: 339995 (C4 (Web Text))

Max Activating Token Index: 186

Text #16

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0350. Min Act: -0.0002

Data Index: 835308 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1277956 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0399. Min Act: -0.0002

Data Index: 799085 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 0.0568. Min Range: -0.0568

Max Act: 0.0376. Min Act: -0.0002

Data Index: 765726 (C4 (Web Text))

Max Activating Token Index: 265