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

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

Neuron 4621 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3407. Min Act: -0.0000

Data Index: 872003 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3460. Min Act: -0.0000

Data Index: 705281 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3443. Min Act: -0.0000

Data Index: 901115 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3141. Min Act: -0.0000

Data Index: 1055241 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.3135. Min Act: -0.0000

Data Index: 398550 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2985. Min Act: -0.0000

Data Index: 546559 (C4 (Web Text))

Max Activating Token Index: 547

Text #6

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2743. Min Act: -0.0000

Data Index: 1083702 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2708. Min Act: -0.0000

Data Index: 646672 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2873. Min Act: -0.0000

Data Index: 35088 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2670. Min Act: -0.0000

Data Index: 249379 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2968. Min Act: -0.0000

Data Index: 458326 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2349. Min Act: -0.0000

Data Index: 65881 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2489. Min Act: -0.0000

Data Index: 389447 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2316. Min Act: -0.0000

Data Index: 1167817 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2609. Min Act: -0.0000

Data Index: 1036448 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2147. Min Act: -0.0000

Data Index: 1054881 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2608. Min Act: -0.0000

Data Index: 407952 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2261. Min Act: -0.0000

Data Index: 778840 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2141. Min Act: -0.0000

Data Index: 510516 (C4 (Web Text))

Max Activating Token Index: 394

Text #19

Max Range: 0.3460. Min Range: -0.3460

Max Act: 0.2190. Min Act: -0.0000

Data Index: 558559 (C4 (Web Text))

Max Activating Token Index: 54