Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 257 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.4668. Min Act: -0.0001

Data Index: 1192954 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.4204. Min Act: -0.0001

Data Index: 584608 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3803. Min Act: -0.0001

Data Index: 614262 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3658. Min Act: -0.0001

Data Index: 865301 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3589. Min Act: -0.0001

Data Index: 1240000 (C4 (Web Text))

Max Activating Token Index: 442

Text #5

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3466. Min Act: -0.0001

Data Index: 1291730 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3494. Min Act: -0.0001

Data Index: 1223727 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.2954. Min Act: -0.0001

Data Index: 901691 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3633. Min Act: -0.0001

Data Index: 262264 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3599. Min Act: -0.0001

Data Index: 617649 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3328. Min Act: -0.0001

Data Index: 732411 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3384. Min Act: -0.0001

Data Index: 324335 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3353. Min Act: -0.0001

Data Index: 1015551 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3223. Min Act: -0.0001

Data Index: 472942 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3374. Min Act: -0.0001

Data Index: 539580 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3258. Min Act: -0.0001

Data Index: 299595 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3350. Min Act: -0.0001

Data Index: 490245 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3408. Min Act: -0.0001

Data Index: 566055 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3005. Min Act: -0.0001

Data Index: 422911 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3219. Min Act: -0.0001

Data Index: 332874 (C4 (Web Text))

Max Activating Token Index: 112