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

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

Neuron 1287 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.4177. Min Act: -0.0000

Data Index: 671621 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.4751. Min Act: -0.0000

Data Index: 542191 (C4 (Web Text))

Max Activating Token Index: 378

Text #2

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.4484. Min Act: -0.0000

Data Index: 448381 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.4480. Min Act: -0.0000

Data Index: 570875 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.4051. Min Act: -0.0000

Data Index: 81725 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.3885. Min Act: -0.0000

Data Index: 284556 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.4007. Min Act: -0.0000

Data Index: 396347 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.3838. Min Act: -0.0000

Data Index: 149073 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.3330. Min Act: -0.0000

Data Index: 960310 (C4 (Web Text))

Max Activating Token Index: 209

Text #9

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.3596. Min Act: 0.0000

Data Index: 896533 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.3518. Min Act: -0.0000

Data Index: 771198 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.3307. Min Act: -0.0000

Data Index: 156916 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.3413. Min Act: -0.0000

Data Index: 192724 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.3402. Min Act: -0.0000

Data Index: 50674 (C4 (Web Text))

Max Activating Token Index: 322

Text #14

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.3614. Min Act: -0.0000

Data Index: 1067203 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.3241. Min Act: -0.0000

Data Index: 576485 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.3292. Min Act: -0.0000

Data Index: 43918 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.3533. Min Act: -0.0000

Data Index: 77921 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.3408. Min Act: -0.0000

Data Index: 392555 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 0.4751. Min Range: -0.4751

Max Act: 0.3257. Min Act: -0.0000

Data Index: 311640 (C4 (Web Text))

Max Activating Token Index: 964