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

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

Neuron 1457 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: 0.6572. Min Range: -0.6572

Max Act: 0.6202. Min Act: -0.0000

Data Index: 986247 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5886. Min Act: -0.0000

Data Index: 262039 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.6572. Min Act: -0.0000

Data Index: 155502 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5691. Min Act: -0.0000

Data Index: 1103326 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5620. Min Act: -0.0001

Data Index: 1271088 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5441. Min Act: -0.0000

Data Index: 1250065 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5486. Min Act: -0.0000

Data Index: 481908 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5440. Min Act: -0.0000

Data Index: 1340266 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5384. Min Act: -0.0000

Data Index: 91853 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5150. Min Act: -0.0000

Data Index: 24863 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5185. Min Act: -0.0000

Data Index: 1338205 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5326. Min Act: 0.0000

Data Index: 742122 (C4 (Web Text))

Max Activating Token Index: 615

Text #12

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5148. Min Act: -0.0001

Data Index: 173206 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5281. Min Act: -0.0001

Data Index: 167175 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4690. Min Act: -0.0000

Data Index: 145113 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4950. Min Act: -0.0000

Data Index: 55819 (C4 (Web Text))

Max Activating Token Index: 684

Text #16

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5100. Min Act: -0.0000

Data Index: 132729 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4930. Min Act: -0.0000

Data Index: 727252 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5243. Min Act: -0.0000

Data Index: 950394 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5028. Min Act: -0.0001

Data Index: 1323425 (C4 (Web Text))

Max Activating Token Index: 41