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

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

Neuron 3344 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: 1.9964. Min Range: -1.9964

Max Act: 1.9964. Min Act: -0.0001

Data Index: 409864 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 1.9964. Min Range: -1.9964

Max Act: 1.9234. Min Act: -0.0001

Data Index: 335902 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 1.9964. Min Range: -1.9964

Max Act: 1.6605. Min Act: -0.0001

Data Index: 1107921 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 1.9964. Min Range: -1.9964

Max Act: 1.7218. Min Act: -0.0001

Data Index: 502181 (C4 (Web Text))

Max Activating Token Index: 926

Text #4

Max Range: 1.9964. Min Range: -1.9964

Max Act: 1.7217. Min Act: -0.0001

Data Index: 675797 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 1.9964. Min Range: -1.9964

Max Act: 1.6162. Min Act: -0.0001

Data Index: 635716 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 1.9964. Min Range: -1.9964

Max Act: 1.5938. Min Act: -0.0001

Data Index: 379567 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 1.9964. Min Range: -1.9964

Max Act: 1.6774. Min Act: -0.0001

Data Index: 268909 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 1.9964. Min Range: -1.9964

Max Act: 1.5768. Min Act: -0.0001

Data Index: 527933 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 1.9964. Min Range: -1.9964

Max Act: 1.6359. Min Act: -0.0001

Data Index: 246671 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 1.9964. Min Range: -1.9964

Max Act: 1.8472. Min Act: -0.0001

Data Index: 14166 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 1.9964. Min Range: -1.9964

Max Act: 1.7140. Min Act: -0.0001

Data Index: 1038413 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 1.9964. Min Range: -1.9964

Max Act: 1.7226. Min Act: -0.0001

Data Index: 1006307 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 1.9964. Min Range: -1.9964

Max Act: 1.6038. Min Act: -0.0001

Data Index: 259269 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 1.9964. Min Range: -1.9964

Max Act: 1.6031. Min Act: -0.0001

Data Index: 250758 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 1.9964. Min Range: -1.9964

Max Act: 1.4660. Min Act: -0.0001

Data Index: 946539 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 1.9964. Min Range: -1.9964

Max Act: 1.5486. Min Act: -0.0001

Data Index: 1341321 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 1.9964. Min Range: -1.9964

Max Act: 1.3785. Min Act: -0.0001

Data Index: 1062209 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 1.9964. Min Range: -1.9964

Max Act: 1.5425. Min Act: -0.0001

Data Index: 115015 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 1.9964. Min Range: -1.9964

Max Act: 1.5543. Min Act: -0.0001

Data Index: 370997 (C4 (Web Text))

Max Activating Token Index: 278