Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1499 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4485. Min Range: -2.4485

Max Act: 2.4485. Min Act: -0.0000

Data Index: 166936 (C4 (Web Text))

Max Activating Token Index: 211

Text #1

Max Range: 2.4485. Min Range: -2.4485

Max Act: 2.2323. Min Act: -0.0000

Data Index: 735604 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 2.4485. Min Range: -2.4485

Max Act: 2.3578. Min Act: -0.0000

Data Index: 418395 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 2.4485. Min Range: -2.4485

Max Act: 2.4460. Min Act: -0.0000

Data Index: 438291 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 2.4485. Min Range: -2.4485

Max Act: 2.1892. Min Act: -0.0000

Data Index: 376117 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 2.4485. Min Range: -2.4485

Max Act: 2.0288. Min Act: -0.0000

Data Index: 20130 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 2.4485. Min Range: -2.4485

Max Act: 2.2349. Min Act: -0.0000

Data Index: 1254555 (C4 (Web Text))

Max Activating Token Index: 155

Text #7

Max Range: 2.4485. Min Range: -2.4485

Max Act: 2.1829. Min Act: -0.0000

Data Index: 83828 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 2.4485. Min Range: -2.4485

Max Act: 2.2070. Min Act: -0.0000

Data Index: 796359 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 2.4485. Min Range: -2.4485

Max Act: 2.1908. Min Act: -0.0000

Data Index: 921267 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 2.4485. Min Range: -2.4485

Max Act: 2.1829. Min Act: -0.0000

Data Index: 477662 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 2.4485. Min Range: -2.4485

Max Act: 2.1456. Min Act: -0.0000

Data Index: 1264744 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 2.4485. Min Range: -2.4485

Max Act: 2.1443. Min Act: -0.0000

Data Index: 407488 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 2.4485. Min Range: -2.4485

Max Act: 2.0031. Min Act: -0.0000

Data Index: 1036513 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 2.4485. Min Range: -2.4485

Max Act: 1.9945. Min Act: -0.0000

Data Index: 462752 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 2.4485. Min Range: -2.4485

Max Act: 2.1002. Min Act: -0.0000

Data Index: 322812 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 2.4485. Min Range: -2.4485

Max Act: 1.9639. Min Act: -0.0000

Data Index: 143940 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 2.4485. Min Range: -2.4485

Max Act: 1.9663. Min Act: -0.0000

Data Index: 939273 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 2.4485. Min Range: -2.4485

Max Act: 2.0956. Min Act: -0.0000

Data Index: 49899 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 2.4485. Min Range: -2.4485

Max Act: 1.9560. Min Act: -0.0000

Data Index: 78857 (C4 (Web Text))

Max Activating Token Index: 628