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

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

Neuron 4595 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5635. Min Range: -3.5635

Max Act: 3.5635. Min Act: -0.0000

Data Index: 457105 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 3.5635. Min Range: -3.5635

Max Act: 3.2964. Min Act: -0.0000

Data Index: 395723 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 3.5635. Min Range: -3.5635

Max Act: 3.1210. Min Act: -0.0000

Data Index: 1048546 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 3.5635. Min Range: -3.5635

Max Act: 2.9923. Min Act: -0.0000

Data Index: 327537 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 3.5635. Min Range: -3.5635

Max Act: 3.2325. Min Act: -0.0000

Data Index: 1100704 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 3.5635. Min Range: -3.5635

Max Act: 3.0531. Min Act: -0.0000

Data Index: 1288994 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 3.5635. Min Range: -3.5635

Max Act: 3.0307. Min Act: -0.0000

Data Index: 401302 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 3.5635. Min Range: -3.5635

Max Act: 2.9472. Min Act: -0.0000

Data Index: 240835 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 3.5635. Min Range: -3.5635

Max Act: 2.8970. Min Act: -0.0000

Data Index: 747076 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 3.5635. Min Range: -3.5635

Max Act: 2.8313. Min Act: -0.0000

Data Index: 357065 (C4 (Web Text))

Max Activating Token Index: 602

Text #10

Max Range: 3.5635. Min Range: -3.5635

Max Act: 2.7892. Min Act: -0.0000

Data Index: 1047964 (C4 (Web Text))

Max Activating Token Index: 858

Text #11

Max Range: 3.5635. Min Range: -3.5635

Max Act: 2.6249. Min Act: -0.0000

Data Index: 161225 (C4 (Web Text))

Max Activating Token Index: 394

Text #12

Max Range: 3.5635. Min Range: -3.5635

Max Act: 2.8616. Min Act: -0.0000

Data Index: 124960 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 3.5635. Min Range: -3.5635

Max Act: 2.5742. Min Act: -0.0000

Data Index: 739462 (C4 (Web Text))

Max Activating Token Index: 430

Text #14

Max Range: 3.5635. Min Range: -3.5635

Max Act: 2.6904. Min Act: -0.0000

Data Index: 173748 (C4 (Web Text))

Max Activating Token Index: 83

Text #15

Max Range: 3.5635. Min Range: -3.5635

Max Act: 2.6622. Min Act: -0.0000

Data Index: 604390 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 3.5635. Min Range: -3.5635

Max Act: 2.6173. Min Act: -0.0000

Data Index: 1132317 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 3.5635. Min Range: -3.5635

Max Act: 2.6108. Min Act: -0.0000

Data Index: 917590 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 3.5635. Min Range: -3.5635

Max Act: 2.5994. Min Act: -0.0000

Data Index: 1003602 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 3.5635. Min Range: -3.5635

Max Act: 2.5872. Min Act: -0.0000

Data Index: 764512 (C4 (Web Text))

Max Activating Token Index: 234