Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5145 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.9884. Min Range: -2.9884

Max Act: 2.9884. Min Act: -0.0000

Data Index: 1011518 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 2.9884. Min Range: -2.9884

Max Act: 2.8141. Min Act: -0.0000

Data Index: 78269 (C4 (Web Text))

Max Activating Token Index: 877

Text #2

Max Range: 2.9884. Min Range: -2.9884

Max Act: 2.8222. Min Act: -0.0000

Data Index: 93522 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 2.9884. Min Range: -2.9884

Max Act: 2.8082. Min Act: -0.0000

Data Index: 178770 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 2.9884. Min Range: -2.9884

Max Act: 2.8357. Min Act: -0.0000

Data Index: 7654 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 2.9884. Min Range: -2.9884

Max Act: 2.5562. Min Act: -0.0000

Data Index: 774130 (C4 (Web Text))

Max Activating Token Index: 650

Text #6

Max Range: 2.9884. Min Range: -2.9884

Max Act: 2.5293. Min Act: -0.0000

Data Index: 1066643 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 2.9884. Min Range: -2.9884

Max Act: 2.8032. Min Act: -0.0000

Data Index: 694722 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 2.9884. Min Range: -2.9884

Max Act: 2.6443. Min Act: -0.0000

Data Index: 235503 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 2.9884. Min Range: -2.9884

Max Act: 2.7466. Min Act: -0.0000

Data Index: 14507 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 2.9884. Min Range: -2.9884

Max Act: 2.7597. Min Act: -0.0000

Data Index: 527331 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 2.9884. Min Range: -2.9884

Max Act: 2.7212. Min Act: -0.0000

Data Index: 769057 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 2.9884. Min Range: -2.9884

Max Act: 2.4866. Min Act: -0.0000

Data Index: 468446 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 2.9884. Min Range: -2.9884

Max Act: 2.4766. Min Act: -0.0000

Data Index: 1094803 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 2.9884. Min Range: -2.9884

Max Act: 2.4876. Min Act: -0.0000

Data Index: 369035 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 2.9884. Min Range: -2.9884

Max Act: 2.2975. Min Act: -0.0000

Data Index: 573760 (C4 (Web Text))

Max Activating Token Index: 947

Text #16

Max Range: 2.9884. Min Range: -2.9884

Max Act: 2.5174. Min Act: -0.0000

Data Index: 710324 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 2.9884. Min Range: -2.9884

Max Act: 2.2602. Min Act: -0.0000

Data Index: 457870 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 2.9884. Min Range: -2.9884

Max Act: 2.4852. Min Act: -0.0000

Data Index: 852515 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 2.9884. Min Range: -2.9884

Max Act: 2.4507. Min Act: -0.0000

Data Index: 812892 (C4 (Web Text))

Max Activating Token Index: 626