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

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

Neuron 3979 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.3478. Min Act: -0.0000

Data Index: 460331 (C4 (Web Text))

Max Activating Token Index: 529

Text #1

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.3010. Min Act: -0.0000

Data Index: 1277232 (C4 (Web Text))

Max Activating Token Index: 758

Text #2

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.2877. Min Act: -0.0001

Data Index: 453987 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.2937. Min Act: -0.0000

Data Index: 568572 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.2779. Min Act: -0.0001

Data Index: 638766 (C4 (Web Text))

Max Activating Token Index: 287

Text #5

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.2883. Min Act: -0.0000

Data Index: 119755 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.2772. Min Act: -0.0001

Data Index: 793273 (C4 (Web Text))

Max Activating Token Index: 67

Text #7

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.2592. Min Act: -0.0001

Data Index: 686987 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.2628. Min Act: -0.0000

Data Index: 748754 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.2708. Min Act: -0.0000

Data Index: 181719 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.2542. Min Act: -0.0000

Data Index: 808938 (C4 (Web Text))

Max Activating Token Index: 446

Text #11

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.2514. Min Act: -0.0001

Data Index: 840955 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.2500. Min Act: -0.0001

Data Index: 170737 (C4 (Web Text))

Max Activating Token Index: 450

Text #13

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.2358. Min Act: -0.0000

Data Index: 229639 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.2274. Min Act: -0.0001

Data Index: 337604 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.2307. Min Act: -0.0001

Data Index: 1092888 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.2229. Min Act: -0.0000

Data Index: 1242455 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.2210. Min Act: -0.0001

Data Index: 443833 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.2174. Min Act: -0.0001

Data Index: 1117608 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 0.3478. Min Range: -0.3478

Max Act: 0.2256. Min Act: -0.0000

Data Index: 424434 (C4 (Web Text))

Max Activating Token Index: 134