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

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

Neuron 1433 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: 2.7182. Min Range: -2.7182

Max Act: 2.7182. Min Act: -0.0001

Data Index: 683985 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 2.7182. Min Range: -2.7182

Max Act: 0.5079. Min Act: -0.0000

Data Index: 1197163 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 2.7182. Min Range: -2.7182

Max Act: 0.0372. Min Act: -0.0001

Data Index: 1265231 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 2.7182. Min Range: -2.7182

Max Act: 0.1217. Min Act: -0.0000

Data Index: 148500 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 2.7182. Min Range: -2.7182

Max Act: 0.1019. Min Act: -0.0000

Data Index: 829244 (C4 (Web Text))

Max Activating Token Index: 658

Text #5

Max Range: 2.7182. Min Range: -2.7182

Max Act: 0.0947. Min Act: -0.0000

Data Index: 1154725 (C4 (Web Text))

Max Activating Token Index: 1001

Text #6

Max Range: 2.7182. Min Range: -2.7182

Max Act: 0.0907. Min Act: -0.0000

Data Index: 897704 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 2.7182. Min Range: -2.7182

Max Act: 0.0941. Min Act: 0.0001

Data Index: 699671 (C4 (Web Text))

Max Activating Token Index: 560

Text #8

Max Range: 2.7182. Min Range: -2.7182

Max Act: 0.1079. Min Act: -0.0000

Data Index: 822419 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 2.7182. Min Range: -2.7182

Max Act: 0.0889. Min Act: -0.0000

Data Index: 266408 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 2.7182. Min Range: -2.7182

Max Act: 0.0871. Min Act: -0.0000

Data Index: 1248873 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 2.7182. Min Range: -2.7182

Max Act: 0.0895. Min Act: -0.0000

Data Index: 1216813 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 2.7182. Min Range: -2.7182

Max Act: 0.0810. Min Act: -0.0000

Data Index: 984177 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 2.7182. Min Range: -2.7182

Max Act: 0.0753. Min Act: -0.0001

Data Index: 1281769 (C4 (Web Text))

Max Activating Token Index: 723

Text #14

Max Range: 2.7182. Min Range: -2.7182

Max Act: 0.0791. Min Act: -0.0000

Data Index: 51940 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 2.7182. Min Range: -2.7182

Max Act: 0.0768. Min Act: 0.0000

Data Index: 538439 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 2.7182. Min Range: -2.7182

Max Act: 0.0687. Min Act: -0.0000

Data Index: 1339848 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 2.7182. Min Range: -2.7182

Max Act: 0.0793. Min Act: 0.0000

Data Index: 588929 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 2.7182. Min Range: -2.7182

Max Act: 0.0777. Min Act: 0.0000

Data Index: 1327819 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 2.7182. Min Range: -2.7182

Max Act: 0.0711. Min Act: -0.0000

Data Index: 1221094 (C4 (Web Text))

Max Activating Token Index: 257