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

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

Neuron 3343 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0000. Min Range: -1.0000

Max Act: 1.0000. Min Act: -0.0000

Data Index: 395775 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8535. Min Act: 0.0001

Data Index: 1040931 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8402. Min Act: -0.0000

Data Index: 584717 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8333. Min Act: -0.0000

Data Index: 7599 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8006. Min Act: -0.0000

Data Index: 1297500 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7955. Min Act: -0.0000

Data Index: 786713 (C4 (Web Text))

Max Activating Token Index: 367

Text #6

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7510. Min Act: -0.0000

Data Index: 800050 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7832. Min Act: -0.0000

Data Index: 67313 (C4 (Web Text))

Max Activating Token Index: 176

Text #8

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7356. Min Act: -0.0000

Data Index: 237948 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7233. Min Act: -0.0000

Data Index: 1014419 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.6979. Min Act: -0.0000

Data Index: 173966 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7119. Min Act: -0.0000

Data Index: 198167 (C4 (Web Text))

Max Activating Token Index: 528

Text #12

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.6597. Min Act: -0.0000

Data Index: 671068 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.6767. Min Act: -0.0000

Data Index: 311818 (C4 (Web Text))

Max Activating Token Index: 436

Text #14

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.6806. Min Act: -0.0000

Data Index: 738087 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7250. Min Act: -0.0000

Data Index: 658303 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.6730. Min Act: -0.0000

Data Index: 26755 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.6453. Min Act: -0.0000

Data Index: 1136490 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.6402. Min Act: -0.0001

Data Index: 275447 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.6479. Min Act: -0.0000

Data Index: 1032702 (C4 (Web Text))

Max Activating Token Index: 395