Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4065 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.5854. Min Act: -0.0000

Data Index: 473534 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.4869. Min Act: -0.0000

Data Index: 1166223 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.5160. Min Act: -0.0001

Data Index: 717160 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.4718. Min Act: -0.0001

Data Index: 1356153 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.4508. Min Act: -0.0000

Data Index: 1272937 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.4456. Min Act: -0.0000

Data Index: 868693 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.4600. Min Act: -0.0001

Data Index: 942843 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.4524. Min Act: -0.0000

Data Index: 396970 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.4292. Min Act: -0.0001

Data Index: 1182818 (C4 (Web Text))

Max Activating Token Index: 925

Text #9

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.4496. Min Act: -0.0001

Data Index: 69878 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.5181. Min Act: -0.0000

Data Index: 507650 (C4 (Web Text))

Max Activating Token Index: 633

Text #11

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.4393. Min Act: -0.0001

Data Index: 350487 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.4040. Min Act: -0.0001

Data Index: 775878 (C4 (Web Text))

Max Activating Token Index: 348

Text #13

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.4029. Min Act: -0.0001

Data Index: 959663 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.3919. Min Act: -0.0001

Data Index: 1298098 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.4058. Min Act: -0.0000

Data Index: 896539 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.3946. Min Act: -0.0001

Data Index: 1096422 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.4030. Min Act: -0.0001

Data Index: 1252730 (C4 (Web Text))

Max Activating Token Index: 567

Text #18

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.4043. Min Act: -0.0000

Data Index: 601654 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 0.5854. Min Range: -0.5854

Max Act: 0.3947. Min Act: -0.0000

Data Index: 830759 (C4 (Web Text))

Max Activating Token Index: 568