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

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

Neuron 1642 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.8628. Min Act: -0.0000

Data Index: 1315953 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.8633. Min Act: -0.0000

Data Index: 419752 (C4 (Web Text))

Max Activating Token Index: 497

Text #2

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.7226. Min Act: -0.0000

Data Index: 1211120 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.5169. Min Act: -0.0000

Data Index: 706796 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.4730. Min Act: -0.0000

Data Index: 699267 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.4149. Min Act: -0.0000

Data Index: 1159122 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.4075. Min Act: -0.0000

Data Index: 12427 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.3941. Min Act: -0.0000

Data Index: 1268246 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.3867. Min Act: -0.0000

Data Index: 86224 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.4025. Min Act: -0.0000

Data Index: 232851 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.3777. Min Act: -0.0000

Data Index: 315823 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.3513. Min Act: -0.0000

Data Index: 208175 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.3885. Min Act: -0.0000

Data Index: 378678 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.3958. Min Act: -0.0000

Data Index: 50372 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.3401. Min Act: -0.0000

Data Index: 442232 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.3454. Min Act: -0.0000

Data Index: 828298 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.3650. Min Act: -0.0000

Data Index: 552372 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.3064. Min Act: -0.0000

Data Index: 990415 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.3887. Min Act: -0.0000

Data Index: 308372 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.8633. Min Range: -0.8633

Max Act: 0.3479. Min Act: -0.0000

Data Index: 302794 (C4 (Web Text))

Max Activating Token Index: 922