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

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

Neuron 3213 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.7295. Min Act: -0.0001

Data Index: 294452 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.6732. Min Act: -0.0001

Data Index: 448254 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5152. Min Act: -0.0001

Data Index: 846323 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5708. Min Act: -0.0001

Data Index: 716299 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5127. Min Act: -0.0001

Data Index: 862715 (C4 (Web Text))

Max Activating Token Index: 909

Text #5

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.4786. Min Act: -0.0000

Data Index: 33564 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5070. Min Act: -0.0000

Data Index: 999081 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.4946. Min Act: -0.0001

Data Index: 833399 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.4982. Min Act: -0.0001

Data Index: 1300457 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.5302. Min Act: -0.0001

Data Index: 927635 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.4577. Min Act: -0.0001

Data Index: 404652 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.4930. Min Act: -0.0001

Data Index: 708102 (C4 (Web Text))

Max Activating Token Index: 269

Text #12

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.4560. Min Act: -0.0000

Data Index: 443307 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.4392. Min Act: -0.0000

Data Index: 1589100 (Python Code)

Max Activating Token Index: 923

Text #14

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.4901. Min Act: -0.0001

Data Index: 798316 (C4 (Web Text))

Max Activating Token Index: 133

Text #15

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.4450. Min Act: -0.0001

Data Index: 894053 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.3923. Min Act: -0.0001

Data Index: 952096 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.4300. Min Act: -0.0001

Data Index: 953956 (C4 (Web Text))

Max Activating Token Index: 509

Text #18

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.4364. Min Act: -0.0001

Data Index: 999036 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 0.7295. Min Range: -0.7295

Max Act: 0.4321. Min Act: -0.0001

Data Index: 1022446 (C4 (Web Text))

Max Activating Token Index: 924