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

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

Neuron 11 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.4102. Min Act: -0.0000

Data Index: 268166 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.0688. Min Act: -0.0000

Data Index: 553807 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 3.4102. Min Range: -3.4102

Max Act: 2.8825. Min Act: -0.0000

Data Index: 1202318 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 3.4102. Min Range: -3.4102

Max Act: 2.9517. Min Act: -0.0000

Data Index: 723233 (C4 (Web Text))

Max Activating Token Index: 299

Text #4

Max Range: 3.4102. Min Range: -3.4102

Max Act: 2.9160. Min Act: -0.0000

Data Index: 1131449 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.0562. Min Act: -0.0000

Data Index: 767501 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 3.4102. Min Range: -3.4102

Max Act: 2.9449. Min Act: -0.0000

Data Index: 555976 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 3.4102. Min Range: -3.4102

Max Act: 3.0768. Min Act: -0.0000

Data Index: 302895 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 3.4102. Min Range: -3.4102

Max Act: 2.9120. Min Act: -0.0000

Data Index: 1202259 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 3.4102. Min Range: -3.4102

Max Act: 2.8732. Min Act: -0.0000

Data Index: 1122206 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 3.4102. Min Range: -3.4102

Max Act: 2.8208. Min Act: -0.0000

Data Index: 688898 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 3.4102. Min Range: -3.4102

Max Act: 2.9499. Min Act: -0.0000

Data Index: 629700 (C4 (Web Text))

Max Activating Token Index: 607

Text #12

Max Range: 3.4102. Min Range: -3.4102

Max Act: 2.7810. Min Act: -0.0000

Data Index: 896972 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 3.4102. Min Range: -3.4102

Max Act: 2.8831. Min Act: -0.0000

Data Index: 1107568 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 3.4102. Min Range: -3.4102

Max Act: 2.6934. Min Act: -0.0000

Data Index: 485107 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 3.4102. Min Range: -3.4102

Max Act: 2.6464. Min Act: -0.0000

Data Index: 1069724 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 3.4102. Min Range: -3.4102

Max Act: 2.6588. Min Act: -0.0000

Data Index: 527119 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 3.4102. Min Range: -3.4102

Max Act: 2.6210. Min Act: -0.0000

Data Index: 1042355 (C4 (Web Text))

Max Activating Token Index: 292

Text #18

Max Range: 3.4102. Min Range: -3.4102

Max Act: 2.9195. Min Act: -0.0000

Data Index: 827356 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 3.4102. Min Range: -3.4102

Max Act: 2.7608. Min Act: -0.0000

Data Index: 942847 (C4 (Web Text))

Max Activating Token Index: 577