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

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

Neuron 607 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: 1.1775. Min Range: -1.1775

Max Act: 1.1203. Min Act: -0.0000

Data Index: 373711 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 1.1775. Min Range: -1.1775

Max Act: 1.1160. Min Act: -0.0000

Data Index: 538432 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 1.1775. Min Range: -1.1775

Max Act: 1.1775. Min Act: -0.0000

Data Index: 754736 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.9745. Min Act: -0.0000

Data Index: 695670 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.9028. Min Act: -0.0000

Data Index: 1005712 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 1.1775. Min Range: -1.1775

Max Act: 1.0060. Min Act: -0.0000

Data Index: 731056 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 1.1775. Min Range: -1.1775

Max Act: 1.0167. Min Act: -0.0000

Data Index: 813396 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.8364. Min Act: -0.0000

Data Index: 742478 (C4 (Web Text))

Max Activating Token Index: 510

Text #8

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.8197. Min Act: -0.0000

Data Index: 63038 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.8437. Min Act: -0.0000

Data Index: 1292071 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.8575. Min Act: -0.0000

Data Index: 74345 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.7881. Min Act: -0.0000

Data Index: 748572 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.8113. Min Act: -0.0000

Data Index: 821730 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.7932. Min Act: -0.0000

Data Index: 436147 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.7539. Min Act: -0.0000

Data Index: 1315031 (C4 (Web Text))

Max Activating Token Index: 181

Text #15

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.7957. Min Act: -0.0000

Data Index: 896293 (C4 (Web Text))

Max Activating Token Index: 308

Text #16

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.7350. Min Act: -0.0000

Data Index: 804140 (C4 (Web Text))

Max Activating Token Index: 633

Text #17

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.7105. Min Act: -0.0000

Data Index: 366167 (C4 (Web Text))

Max Activating Token Index: 938

Text #18

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.7698. Min Act: -0.0000

Data Index: 1042727 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 1.1775. Min Range: -1.1775

Max Act: 0.7658. Min Act: -0.0000

Data Index: 12099 (C4 (Web Text))

Max Activating Token Index: 761