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

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

Neuron 2104 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.8755. Min Range: -1.8755

Max Act: 1.8755. Min Act: -0.0002

Data Index: 1270448 (C4 (Web Text))

Max Activating Token Index: 631

Text #1

Max Range: 1.8755. Min Range: -1.8755

Max Act: 1.7189. Min Act: -0.0002

Data Index: 201317 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 1.8755. Min Range: -1.8755

Max Act: 1.7126. Min Act: -0.0002

Data Index: 119746 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 1.8755. Min Range: -1.8755

Max Act: 1.6732. Min Act: -0.0002

Data Index: 227456 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 1.8755. Min Range: -1.8755

Max Act: 1.6467. Min Act: -0.0002

Data Index: 713817 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 1.8755. Min Range: -1.8755

Max Act: 1.6060. Min Act: -0.0002

Data Index: 1114515 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 1.8755. Min Range: -1.8755

Max Act: 1.6130. Min Act: -0.0002

Data Index: 1315856 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 1.8755. Min Range: -1.8755

Max Act: 1.6087. Min Act: -0.0002

Data Index: 1280803 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 1.8755. Min Range: -1.8755

Max Act: 1.6165. Min Act: -0.0002

Data Index: 589750 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 1.8755. Min Range: -1.8755

Max Act: 1.6423. Min Act: -0.0002

Data Index: 482711 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 1.8755. Min Range: -1.8755

Max Act: 1.5365. Min Act: -0.0002

Data Index: 180437 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 1.8755. Min Range: -1.8755

Max Act: 1.5356. Min Act: -0.0002

Data Index: 1030944 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 1.8755. Min Range: -1.8755

Max Act: 1.5646. Min Act: -0.0002

Data Index: 135073 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 1.8755. Min Range: -1.8755

Max Act: 1.5328. Min Act: -0.0002

Data Index: 3960 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 1.8755. Min Range: -1.8755

Max Act: 1.5609. Min Act: -0.0002

Data Index: 1137353 (C4 (Web Text))

Max Activating Token Index: 605

Text #15

Max Range: 1.8755. Min Range: -1.8755

Max Act: 1.5050. Min Act: -0.0002

Data Index: 83619 (C4 (Web Text))

Max Activating Token Index: 48

Text #16

Max Range: 1.8755. Min Range: -1.8755

Max Act: 1.5512. Min Act: -0.0002

Data Index: 1004059 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 1.8755. Min Range: -1.8755

Max Act: 1.4927. Min Act: -0.0002

Data Index: 860026 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 1.8755. Min Range: -1.8755

Max Act: 1.5095. Min Act: -0.0002

Data Index: 1096474 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 1.8755. Min Range: -1.8755

Max Act: 1.4928. Min Act: -0.0002

Data Index: 700229 (C4 (Web Text))

Max Activating Token Index: 11