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

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

Neuron 4051 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: 1.1385. Min Range: -1.1385

Max Act: 1.1385. Min Act: -0.0000

Data Index: 701521 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 1.1385. Min Range: -1.1385

Max Act: 1.0414. Min Act: -0.0000

Data Index: 939632 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 1.1385. Min Range: -1.1385

Max Act: 1.0572. Min Act: 0.0000

Data Index: 101480 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 1.1385. Min Range: -1.1385

Max Act: 0.8585. Min Act: -0.0000

Data Index: 503264 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 1.1385. Min Range: -1.1385

Max Act: 0.9034. Min Act: -0.0000

Data Index: 497233 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 1.1385. Min Range: -1.1385

Max Act: 0.8376. Min Act: -0.0000

Data Index: 22520 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 1.1385. Min Range: -1.1385

Max Act: 0.8608. Min Act: -0.0000

Data Index: 1321939 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 1.1385. Min Range: -1.1385

Max Act: 0.8125. Min Act: -0.0000

Data Index: 100211 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 1.1385. Min Range: -1.1385

Max Act: 0.8041. Min Act: -0.0000

Data Index: 974842 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 1.1385. Min Range: -1.1385

Max Act: 0.7385. Min Act: -0.0000

Data Index: 569162 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 1.1385. Min Range: -1.1385

Max Act: 0.6850. Min Act: -0.0000

Data Index: 1136746 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 1.1385. Min Range: -1.1385

Max Act: 0.6661. Min Act: -0.0000

Data Index: 46675 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 1.1385. Min Range: -1.1385

Max Act: 0.6997. Min Act: -0.0000

Data Index: 370621 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 1.1385. Min Range: -1.1385

Max Act: 0.6943. Min Act: -0.0000

Data Index: 949262 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 1.1385. Min Range: -1.1385

Max Act: 0.6872. Min Act: -0.0000

Data Index: 147645 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 1.1385. Min Range: -1.1385

Max Act: 0.6896. Min Act: -0.0000

Data Index: 511665 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 1.1385. Min Range: -1.1385

Max Act: 0.6723. Min Act: -0.0000

Data Index: 972231 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 1.1385. Min Range: -1.1385

Max Act: 0.6649. Min Act: -0.0000

Data Index: 888593 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 1.1385. Min Range: -1.1385

Max Act: 0.6329. Min Act: -0.0000

Data Index: 507425 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 1.1385. Min Range: -1.1385

Max Act: 0.6250. Min Act: -0.0000

Data Index: 1037239 (C4 (Web Text))

Max Activating Token Index: 784