Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3622 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0567. Min Act: -0.0001

Data Index: 655031 (C4 (Web Text))

Max Activating Token Index: 524

Text #1

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0541. Min Act: -0.0001

Data Index: 103773 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0483. Min Act: -0.0001

Data Index: 30847 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0510. Min Act: -0.0001

Data Index: 1197569 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0506. Min Act: -0.0001

Data Index: 758839 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0447. Min Act: -0.0001

Data Index: 745814 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0463. Min Act: -0.0001

Data Index: 433435 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0490. Min Act: -0.0001

Data Index: 1278591 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0459. Min Act: -0.0001

Data Index: 1232233 (C4 (Web Text))

Max Activating Token Index: 430

Text #9

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0457. Min Act: -0.0001

Data Index: 559639 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0413. Min Act: -0.0001

Data Index: 1273412 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0451. Min Act: -0.0001

Data Index: 1095921 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0432. Min Act: -0.0001

Data Index: 118751 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0432. Min Act: -0.0001

Data Index: 429000 (C4 (Web Text))

Max Activating Token Index: 830

Text #14

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0424. Min Act: -0.0001

Data Index: 173788 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0413. Min Act: -0.0001

Data Index: 985260 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0423. Min Act: -0.0001

Data Index: 468748 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0437. Min Act: -0.0001

Data Index: 574862 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0423. Min Act: -0.0001

Data Index: 1190805 (C4 (Web Text))

Max Activating Token Index: 547

Text #19

Max Range: 0.0567. Min Range: -0.0567

Max Act: 0.0403. Min Act: -0.0001

Data Index: 449920 (C4 (Web Text))

Max Activating Token Index: 299