Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5155 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.5087. Min Act: -0.0001

Data Index: 407352 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.5548. Min Act: -0.0001

Data Index: 81931 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4961. Min Act: -0.0001

Data Index: 1217544 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.5236. Min Act: -0.0001

Data Index: 586069 (C4 (Web Text))

Max Activating Token Index: 875

Text #4

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4925. Min Act: -0.0001

Data Index: 786281 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4663. Min Act: -0.0001

Data Index: 1026170 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4872. Min Act: -0.0001

Data Index: 887397 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4694. Min Act: -0.0001

Data Index: 1161239 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.5191. Min Act: -0.0001

Data Index: 1098757 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4830. Min Act: -0.0001

Data Index: 81821 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.5003. Min Act: -0.0001

Data Index: 1339887 (C4 (Web Text))

Max Activating Token Index: 30

Text #11

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4497. Min Act: -0.0001

Data Index: 506434 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.5060. Min Act: -0.0001

Data Index: 971953 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4723. Min Act: -0.0001

Data Index: 410104 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4682. Min Act: -0.0001

Data Index: 170345 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4297. Min Act: -0.0001

Data Index: 1047669 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.3802. Min Act: -0.0001

Data Index: 687640 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.5086. Min Act: -0.0001

Data Index: 844281 (C4 (Web Text))

Max Activating Token Index: 217

Text #18

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.3954. Min Act: -0.0001

Data Index: 1222540 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 0.5548. Min Range: -0.5548

Max Act: 0.4913. Min Act: -0.0001

Data Index: 932937 (C4 (Web Text))

Max Activating Token Index: 580