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

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

Neuron 3107 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: 0.4578. Min Range: -0.4578

Max Act: 0.4578. Min Act: -0.0001

Data Index: 984909 (C4 (Web Text))

Max Activating Token Index: 483

Text #1

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.4042. Min Act: -0.0001

Data Index: 970335 (C4 (Web Text))

Max Activating Token Index: 415

Text #2

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.4106. Min Act: -0.0000

Data Index: 271777 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.3834. Min Act: -0.0001

Data Index: 262350 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.4008. Min Act: -0.0001

Data Index: 1135507 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.3683. Min Act: -0.0001

Data Index: 529013 (C4 (Web Text))

Max Activating Token Index: 206

Text #6

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.3605. Min Act: -0.0001

Data Index: 20361 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.3432. Min Act: -0.0001

Data Index: 384582 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.3115. Min Act: -0.0001

Data Index: 757732 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.3198. Min Act: -0.0001

Data Index: 850004 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.3181. Min Act: -0.0001

Data Index: 657434 (C4 (Web Text))

Max Activating Token Index: 153

Text #11

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.3378. Min Act: -0.0001

Data Index: 17409 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.3236. Min Act: -0.0001

Data Index: 1226799 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.3288. Min Act: -0.0001

Data Index: 1062003 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.3071. Min Act: -0.0001

Data Index: 722155 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.3176. Min Act: -0.0001

Data Index: 189373 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.3158. Min Act: -0.0001

Data Index: 1039817 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.3261. Min Act: -0.0001

Data Index: 667453 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.3140. Min Act: -0.0001

Data Index: 1357159 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 0.4578. Min Range: -0.4578

Max Act: 0.3115. Min Act: -0.0001

Data Index: 1035076 (C4 (Web Text))

Max Activating Token Index: 914