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

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

Neuron 2345 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: 5.0433. Min Range: -5.0433

Max Act: 5.0433. Min Act: -0.0000

Data Index: 746150 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 5.0433. Min Range: -5.0433

Max Act: 4.4748. Min Act: -0.0000

Data Index: 704378 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 5.0433. Min Range: -5.0433

Max Act: 4.4128. Min Act: -0.0000

Data Index: 768873 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 5.0433. Min Range: -5.0433

Max Act: 3.9782. Min Act: -0.0000

Data Index: 703813 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 5.0433. Min Range: -5.0433

Max Act: 3.5262. Min Act: -0.0000

Data Index: 690420 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 5.0433. Min Range: -5.0433

Max Act: 3.3436. Min Act: -0.0000

Data Index: 1281941 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 5.0433. Min Range: -5.0433

Max Act: 3.9872. Min Act: -0.0000

Data Index: 512010 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 5.0433. Min Range: -5.0433

Max Act: 3.4527. Min Act: -0.0000

Data Index: 1232274 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 5.0433. Min Range: -5.0433

Max Act: 3.3037. Min Act: -0.0000

Data Index: 1334825 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 5.0433. Min Range: -5.0433

Max Act: 3.7533. Min Act: -0.0000

Data Index: 697662 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 5.0433. Min Range: -5.0433

Max Act: 3.3633. Min Act: -0.0000

Data Index: 78356 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 5.0433. Min Range: -5.0433

Max Act: 3.1723. Min Act: -0.0000

Data Index: 1217186 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 5.0433. Min Range: -5.0433

Max Act: 3.1819. Min Act: -0.0000

Data Index: 994269 (C4 (Web Text))

Max Activating Token Index: 921

Text #13

Max Range: 5.0433. Min Range: -5.0433

Max Act: 3.4948. Min Act: -0.0000

Data Index: 861486 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 5.0433. Min Range: -5.0433

Max Act: 3.3060. Min Act: -0.0000

Data Index: 360162 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 5.0433. Min Range: -5.0433

Max Act: 3.4455. Min Act: -0.0000

Data Index: 859678 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 5.0433. Min Range: -5.0433

Max Act: 3.1074. Min Act: -0.0000

Data Index: 470266 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 5.0433. Min Range: -5.0433

Max Act: 3.2610. Min Act: -0.0000

Data Index: 1253187 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 5.0433. Min Range: -5.0433

Max Act: 2.6921. Min Act: -0.0000

Data Index: 1012377 (C4 (Web Text))

Max Activating Token Index: 803

Text #19

Max Range: 5.0433. Min Range: -5.0433

Max Act: 3.4178. Min Act: -0.0000

Data Index: 1197638 (C4 (Web Text))

Max Activating Token Index: 63