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

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

Neuron 5311 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.4561. Min Act: -0.0002

Data Index: 1315351 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.4573. Min Act: -0.0002

Data Index: 343171 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.4464. Min Act: -0.0002

Data Index: 963787 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.4142. Min Act: -0.0002

Data Index: 1159244 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.4138. Min Act: -0.0002

Data Index: 249150 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3751. Min Act: -0.0002

Data Index: 625394 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3727. Min Act: -0.0002

Data Index: 933492 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3664. Min Act: -0.0002

Data Index: 965790 (C4 (Web Text))

Max Activating Token Index: 751

Text #8

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3852. Min Act: -0.0002

Data Index: 380164 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3673. Min Act: -0.0002

Data Index: 24602 (C4 (Web Text))

Max Activating Token Index: 330

Text #10

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3697. Min Act: -0.0002

Data Index: 905160 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3681. Min Act: -0.0002

Data Index: 981498 (C4 (Web Text))

Max Activating Token Index: 229

Text #12

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3599. Min Act: -0.0002

Data Index: 1132070 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3499. Min Act: -0.0002

Data Index: 275562 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3584. Min Act: -0.0002

Data Index: 299244 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3613. Min Act: -0.0002

Data Index: 1341206 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3489. Min Act: -0.0002

Data Index: 1198562 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3350. Min Act: -0.0002

Data Index: 373251 (C4 (Web Text))

Max Activating Token Index: 611

Text #18

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3459. Min Act: -0.0002

Data Index: 594014 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 0.4573. Min Range: -0.4573

Max Act: 0.3429. Min Act: -0.0002

Data Index: 1189802 (C4 (Web Text))

Max Activating Token Index: 733