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

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

Neuron 2924 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4902. Min Act: -0.0001

Data Index: 267322 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4681. Min Act: -0.0001

Data Index: 48254 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4627. Min Act: -0.0001

Data Index: 1314405 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4542. Min Act: -0.0001

Data Index: 216959 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4345. Min Act: -0.0001

Data Index: 294677 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4446. Min Act: -0.0001

Data Index: 992340 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4469. Min Act: -0.0001

Data Index: 1283582 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4471. Min Act: -0.0001

Data Index: 936235 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4522. Min Act: -0.0001

Data Index: 1063407 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4165. Min Act: -0.0001

Data Index: 1025822 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4426. Min Act: -0.0001

Data Index: 536312 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4258. Min Act: -0.0001

Data Index: 800974 (C4 (Web Text))

Max Activating Token Index: 44

Text #12

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4135. Min Act: -0.0001

Data Index: 1286626 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4031. Min Act: -0.0001

Data Index: 543252 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4138. Min Act: -0.0001

Data Index: 1116932 (C4 (Web Text))

Max Activating Token Index: 46

Text #15

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3955. Min Act: -0.0001

Data Index: 233801 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4063. Min Act: -0.0001

Data Index: 741310 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.4059. Min Act: -0.0001

Data Index: 1009507 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3898. Min Act: -0.0001

Data Index: 418585 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 0.4902. Min Range: -0.4902

Max Act: 0.3873. Min Act: -0.0001

Data Index: 569373 (C4 (Web Text))

Max Activating Token Index: 970