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

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

Neuron 16 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: 5.6261. Min Range: -5.6261

Max Act: 5.6261. Min Act: -0.0001

Data Index: 1143546 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 5.6261. Min Range: -5.6261

Max Act: 5.2796. Min Act: -0.0001

Data Index: 283109 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 5.6261. Min Range: -5.6261

Max Act: 5.3100. Min Act: -0.0001

Data Index: 186214 (C4 (Web Text))

Max Activating Token Index: 98

Text #3

Max Range: 5.6261. Min Range: -5.6261

Max Act: 5.2785. Min Act: -0.0001

Data Index: 1266691 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 5.6261. Min Range: -5.6261

Max Act: 4.6771. Min Act: -0.0001

Data Index: 53089 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 5.6261. Min Range: -5.6261

Max Act: 4.6660. Min Act: -0.0001

Data Index: 1122329 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 5.6261. Min Range: -5.6261

Max Act: 4.2549. Min Act: -0.0001

Data Index: 925368 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 5.6261. Min Range: -5.6261

Max Act: 4.4002. Min Act: -0.0001

Data Index: 606885 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 5.6261. Min Range: -5.6261

Max Act: 4.2781. Min Act: -0.0001

Data Index: 1275416 (C4 (Web Text))

Max Activating Token Index: 544

Text #9

Max Range: 5.6261. Min Range: -5.6261

Max Act: 4.1103. Min Act: -0.0001

Data Index: 574744 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 5.6261. Min Range: -5.6261

Max Act: 4.0094. Min Act: -0.0001

Data Index: 301353 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 5.6261. Min Range: -5.6261

Max Act: 4.1161. Min Act: -0.0001

Data Index: 1043532 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 5.6261. Min Range: -5.6261

Max Act: 4.2273. Min Act: -0.0001

Data Index: 995110 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 5.6261. Min Range: -5.6261

Max Act: 3.9156. Min Act: -0.0001

Data Index: 642006 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 5.6261. Min Range: -5.6261

Max Act: 3.9731. Min Act: -0.0001

Data Index: 285509 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 5.6261. Min Range: -5.6261

Max Act: 3.9975. Min Act: -0.0001

Data Index: 1091643 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 5.6261. Min Range: -5.6261

Max Act: 3.7943. Min Act: -0.0001

Data Index: 635347 (C4 (Web Text))

Max Activating Token Index: 1019

Text #17

Max Range: 5.6261. Min Range: -5.6261

Max Act: 3.9306. Min Act: -0.0001

Data Index: 1030679 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 5.6261. Min Range: -5.6261

Max Act: 3.7993. Min Act: -0.0001

Data Index: 445031 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 5.6261. Min Range: -5.6261

Max Act: 4.0505. Min Act: -0.0001

Data Index: 420691 (C4 (Web Text))

Max Activating Token Index: 733