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

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

Neuron 5500 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7135. Min Range: -3.7135

Max Act: 3.6941. Min Act: -0.0000

Data Index: 166674 (C4 (Web Text))

Max Activating Token Index: 85

Text #1

Max Range: 3.7135. Min Range: -3.7135

Max Act: 3.6643. Min Act: -0.0000

Data Index: 699258 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 3.7135. Min Range: -3.7135

Max Act: 3.7135. Min Act: -0.0001

Data Index: 371192 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 3.7135. Min Range: -3.7135

Max Act: 3.4528. Min Act: -0.0001

Data Index: 848289 (C4 (Web Text))

Max Activating Token Index: 86

Text #4

Max Range: 3.7135. Min Range: -3.7135

Max Act: 3.5607. Min Act: -0.0000

Data Index: 1105638 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 3.7135. Min Range: -3.7135

Max Act: 3.2038. Min Act: -0.0000

Data Index: 999904 (C4 (Web Text))

Max Activating Token Index: 372

Text #6

Max Range: 3.7135. Min Range: -3.7135

Max Act: 3.4542. Min Act: -0.0001

Data Index: 591694 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 3.7135. Min Range: -3.7135

Max Act: 3.4489. Min Act: -0.0001

Data Index: 344122 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 3.7135. Min Range: -3.7135

Max Act: 3.2881. Min Act: -0.0001

Data Index: 851545 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 3.7135. Min Range: -3.7135

Max Act: 3.3989. Min Act: -0.0000

Data Index: 835671 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 3.7135. Min Range: -3.7135

Max Act: 3.0038. Min Act: -0.0000

Data Index: 1166091 (C4 (Web Text))

Max Activating Token Index: 200

Text #11

Max Range: 3.7135. Min Range: -3.7135

Max Act: 3.4260. Min Act: -0.0000

Data Index: 215897 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 3.7135. Min Range: -3.7135

Max Act: 3.2833. Min Act: -0.0001

Data Index: 1044996 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 3.7135. Min Range: -3.7135

Max Act: 3.1006. Min Act: -0.0000

Data Index: 897203 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 3.7135. Min Range: -3.7135

Max Act: 3.2316. Min Act: -0.0001

Data Index: 1359207 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 3.7135. Min Range: -3.7135

Max Act: 3.0666. Min Act: -0.0000

Data Index: 517125 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 3.7135. Min Range: -3.7135

Max Act: 3.1799. Min Act: -0.0000

Data Index: 187205 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 3.7135. Min Range: -3.7135

Max Act: 3.1684. Min Act: -0.0001

Data Index: 21440 (C4 (Web Text))

Max Activating Token Index: 17

Text #18

Max Range: 3.7135. Min Range: -3.7135

Max Act: 3.1318. Min Act: -0.0000

Data Index: 753873 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 3.7135. Min Range: -3.7135

Max Act: 3.1425. Min Act: -0.0000

Data Index: 982591 (C4 (Web Text))

Max Activating Token Index: 130