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

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

Neuron 2888 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7041. Min Range: -3.7041

Max Act: 3.7041. Min Act: -0.0000

Data Index: 52671 (C4 (Web Text))

Max Activating Token Index: 475

Text #1

Max Range: 3.7041. Min Range: -3.7041

Max Act: 2.8651. Min Act: -0.0000

Data Index: 760027 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 3.7041. Min Range: -3.7041

Max Act: 3.3218. Min Act: -0.0000

Data Index: 354070 (C4 (Web Text))

Max Activating Token Index: 959

Text #3

Max Range: 3.7041. Min Range: -3.7041

Max Act: 3.0339. Min Act: -0.0000

Data Index: 1125493 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 3.7041. Min Range: -3.7041

Max Act: 2.9203. Min Act: -0.0000

Data Index: 1235070 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 3.7041. Min Range: -3.7041

Max Act: 2.7256. Min Act: -0.0000

Data Index: 710360 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 3.7041. Min Range: -3.7041

Max Act: 2.8383. Min Act: -0.0000

Data Index: 1202004 (C4 (Web Text))

Max Activating Token Index: 908

Text #7

Max Range: 3.7041. Min Range: -3.7041

Max Act: 2.9692. Min Act: -0.0000

Data Index: 533948 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 3.7041. Min Range: -3.7041

Max Act: 2.4443. Min Act: -0.0000

Data Index: 878183 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 3.7041. Min Range: -3.7041

Max Act: 2.7829. Min Act: -0.0000

Data Index: 985599 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 3.7041. Min Range: -3.7041

Max Act: 2.7571. Min Act: -0.0000

Data Index: 528369 (C4 (Web Text))

Max Activating Token Index: 969

Text #11

Max Range: 3.7041. Min Range: -3.7041

Max Act: 2.7618. Min Act: -0.0000

Data Index: 97154 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 3.7041. Min Range: -3.7041

Max Act: 2.7084. Min Act: -0.0000

Data Index: 1069459 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 3.7041. Min Range: -3.7041

Max Act: 2.7295. Min Act: -0.0000

Data Index: 649193 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 3.7041. Min Range: -3.7041

Max Act: 2.6596. Min Act: -0.0000

Data Index: 1010457 (C4 (Web Text))

Max Activating Token Index: 254

Text #15

Max Range: 3.7041. Min Range: -3.7041

Max Act: 2.6604. Min Act: -0.0000

Data Index: 365370 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 3.7041. Min Range: -3.7041

Max Act: 2.6184. Min Act: -0.0000

Data Index: 774942 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 3.7041. Min Range: -3.7041

Max Act: 2.4503. Min Act: -0.0000

Data Index: 512306 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 3.7041. Min Range: -3.7041

Max Act: 2.5692. Min Act: -0.0000

Data Index: 75360 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 3.7041. Min Range: -3.7041

Max Act: 2.4305. Min Act: -0.0000

Data Index: 1103655 (C4 (Web Text))

Max Activating Token Index: 686