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

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

Neuron 604 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: 0.4564. Min Range: -0.4564

Max Act: 0.4564. Min Act: -0.0001

Data Index: 465752 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.4369. Min Act: -0.0001

Data Index: 804326 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3947. Min Act: -0.0001

Data Index: 1066790 (C4 (Web Text))

Max Activating Token Index: 880

Text #3

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3854. Min Act: -0.0001

Data Index: 153322 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3564. Min Act: -0.0001

Data Index: 1275122 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3564. Min Act: -0.0001

Data Index: 314191 (C4 (Web Text))

Max Activating Token Index: 3

Text #6

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3727. Min Act: -0.0001

Data Index: 185852 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3496. Min Act: -0.0001

Data Index: 804970 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3319. Min Act: -0.0001

Data Index: 236707 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3226. Min Act: -0.0001

Data Index: 744785 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3205. Min Act: -0.0001

Data Index: 863975 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3164. Min Act: -0.0001

Data Index: 35807 (C4 (Web Text))

Max Activating Token Index: 5

Text #12

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3049. Min Act: -0.0001

Data Index: 1211390 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3240. Min Act: -0.0001

Data Index: 429838 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3017. Min Act: -0.0001

Data Index: 1141058 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3198. Min Act: -0.0001

Data Index: 800897 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3158. Min Act: -0.0001

Data Index: 1087602 (C4 (Web Text))

Max Activating Token Index: 315

Text #17

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3158. Min Act: -0.0001

Data Index: 693017 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3051. Min Act: -0.0001

Data Index: 138655 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 0.4564. Min Range: -0.4564

Max Act: 0.3038. Min Act: -0.0001

Data Index: 535007 (C4 (Web Text))

Max Activating Token Index: 483