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

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

Neuron 427 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: 0.3122. Min Range: -0.3122

Max Act: 0.3122. Min Act: -0.0001

Data Index: 64412 (C4 (Web Text))

Max Activating Token Index: 125

Text #1

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2801. Min Act: -0.0001

Data Index: 120477 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2962. Min Act: -0.0001

Data Index: 1117124 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2779. Min Act: -0.0001

Data Index: 538797 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2637. Min Act: -0.0001

Data Index: 363641 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2838. Min Act: -0.0001

Data Index: 1153248 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2807. Min Act: -0.0001

Data Index: 1348933 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2536. Min Act: -0.0001

Data Index: 842487 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2661. Min Act: -0.0001

Data Index: 307635 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2549. Min Act: -0.0001

Data Index: 617935 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2530. Min Act: -0.0001

Data Index: 274141 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2609. Min Act: -0.0001

Data Index: 1196137 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2524. Min Act: -0.0001

Data Index: 1132743 (C4 (Web Text))

Max Activating Token Index: 785

Text #13

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2495. Min Act: -0.0001

Data Index: 115573 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2398. Min Act: -0.0001

Data Index: 556668 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2487. Min Act: -0.0001

Data Index: 423216 (C4 (Web Text))

Max Activating Token Index: 183

Text #16

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2377. Min Act: -0.0001

Data Index: 450434 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2559. Min Act: -0.0001

Data Index: 138425 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2447. Min Act: -0.0001

Data Index: 1133751 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 0.3122. Min Range: -0.3122

Max Act: 0.2351. Min Act: -0.0001

Data Index: 1241122 (C4 (Web Text))

Max Activating Token Index: 937