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

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

Neuron 3053 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: 0.3994. Min Range: -0.3994

Max Act: 0.3994. Min Act: -0.0001

Data Index: 136063 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 0.3994. Min Range: -0.3994

Max Act: 0.3119. Min Act: -0.0001

Data Index: 126009 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 0.3994. Min Range: -0.3994

Max Act: 0.2866. Min Act: -0.0001

Data Index: 571292 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.3994. Min Range: -0.3994

Max Act: 0.2796. Min Act: -0.0001

Data Index: 1090351 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 0.3994. Min Range: -0.3994

Max Act: 0.2556. Min Act: -0.0001

Data Index: 481254 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 0.3994. Min Range: -0.3994

Max Act: 0.2516. Min Act: -0.0001

Data Index: 260696 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 0.3994. Min Range: -0.3994

Max Act: 0.2468. Min Act: -0.0001

Data Index: 94774 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 0.3994. Min Range: -0.3994

Max Act: 0.2461. Min Act: -0.0001

Data Index: 1165323 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 0.3994. Min Range: -0.3994

Max Act: 0.2431. Min Act: -0.0001

Data Index: 458497 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.3994. Min Range: -0.3994

Max Act: 0.2500. Min Act: -0.0001

Data Index: 496179 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 0.3994. Min Range: -0.3994

Max Act: 0.2375. Min Act: -0.0001

Data Index: 952210 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.3994. Min Range: -0.3994

Max Act: 0.2342. Min Act: -0.0001

Data Index: 17696 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 0.3994. Min Range: -0.3994

Max Act: 0.2494. Min Act: -0.0001

Data Index: 779343 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 0.3994. Min Range: -0.3994

Max Act: 0.2334. Min Act: -0.0001

Data Index: 1127948 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 0.3994. Min Range: -0.3994

Max Act: 0.2296. Min Act: -0.0001

Data Index: 1336060 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 0.3994. Min Range: -0.3994

Max Act: 0.2311. Min Act: -0.0001

Data Index: 353 (C4 (Web Text))

Max Activating Token Index: 608

Text #16

Max Range: 0.3994. Min Range: -0.3994

Max Act: 0.2314. Min Act: -0.0001

Data Index: 206387 (C4 (Web Text))

Max Activating Token Index: 877

Text #17

Max Range: 0.3994. Min Range: -0.3994

Max Act: 0.2451. Min Act: -0.0001

Data Index: 213689 (C4 (Web Text))

Max Activating Token Index: 540

Text #18

Max Range: 0.3994. Min Range: -0.3994

Max Act: 0.2335. Min Act: -0.0001

Data Index: 1017878 (C4 (Web Text))

Max Activating Token Index: 201

Text #19

Max Range: 0.3994. Min Range: -0.3994

Max Act: 0.2253. Min Act: -0.0001

Data Index: 1253054 (C4 (Web Text))

Max Activating Token Index: 946