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

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

Neuron 5072 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.6394. Min Act: -0.0000

Data Index: 675451 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.6175. Min Act: -0.0001

Data Index: 1045540 (C4 (Web Text))

Max Activating Token Index: 828

Text #2

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.5749. Min Act: -0.0001

Data Index: 202168 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.5622. Min Act: -0.0001

Data Index: 1148941 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.5462. Min Act: -0.0001

Data Index: 64143 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.5254. Min Act: -0.0001

Data Index: 261707 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4762. Min Act: -0.0001

Data Index: 934773 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.5357. Min Act: -0.0001

Data Index: 869388 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.5008. Min Act: -0.0001

Data Index: 711705 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4442. Min Act: -0.0001

Data Index: 113684 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4799. Min Act: -0.0001

Data Index: 969961 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4230. Min Act: -0.0001

Data Index: 279799 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4475. Min Act: -0.0001

Data Index: 302996 (C4 (Web Text))

Max Activating Token Index: 92

Text #13

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4222. Min Act: -0.0001

Data Index: 94150 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4451. Min Act: -0.0001

Data Index: 499162 (C4 (Web Text))

Max Activating Token Index: 503

Text #15

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4110. Min Act: -0.0001

Data Index: 198950 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4032. Min Act: -0.0001

Data Index: 525270 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4177. Min Act: -0.0001

Data Index: 1183062 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4139. Min Act: -0.0000

Data Index: 1446423 (Python Code)

Max Activating Token Index: 1001

Text #19

Max Range: 0.6394. Min Range: -0.6394

Max Act: 0.4152. Min Act: -0.0001

Data Index: 854006 (C4 (Web Text))

Max Activating Token Index: 665