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

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

Neuron 3172 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: 0.4972. Min Range: -0.4972

Max Act: 0.4972. Min Act: -0.0001

Data Index: 1484797 (Python Code)

Max Activating Token Index: 795

Text #1

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4723. Min Act: -0.0001

Data Index: 1500426 (Python Code)

Max Activating Token Index: 938

Text #2

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4802. Min Act: -0.0001

Data Index: 1445979 (Python Code)

Max Activating Token Index: 702

Text #3

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4673. Min Act: -0.0001

Data Index: 1528076 (Python Code)

Max Activating Token Index: 376

Text #4

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4610. Min Act: -0.0001

Data Index: 1617001 (Python Code)

Max Activating Token Index: 490

Text #5

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4607. Min Act: -0.0001

Data Index: 1563858 (Python Code)

Max Activating Token Index: 774

Text #6

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4691. Min Act: -0.0001

Data Index: 1410791 (Python Code)

Max Activating Token Index: 498

Text #7

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4648. Min Act: -0.0001

Data Index: 1512219 (Python Code)

Max Activating Token Index: 997

Text #8

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4572. Min Act: -0.0001

Data Index: 1550711 (Python Code)

Max Activating Token Index: 780

Text #9

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4581. Min Act: -0.0001

Data Index: 1372199 (Python Code)

Max Activating Token Index: 163

Text #10

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4271. Min Act: -0.0001

Data Index: 1400159 (Python Code)

Max Activating Token Index: 601

Text #11

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4313. Min Act: -0.0001

Data Index: 1412076 (Python Code)

Max Activating Token Index: 492

Text #12

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4480. Min Act: -0.0001

Data Index: 1361559 (Python Code)

Max Activating Token Index: 540

Text #13

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4340. Min Act: -0.0001

Data Index: 1418385 (Python Code)

Max Activating Token Index: 317

Text #14

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4196. Min Act: -0.0001

Data Index: 1560966 (Python Code)

Max Activating Token Index: 764

Text #15

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4290. Min Act: -0.0001

Data Index: 1432099 (Python Code)

Max Activating Token Index: 122

Text #16

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4512. Min Act: -0.0001

Data Index: 1365253 (Python Code)

Max Activating Token Index: 464

Text #17

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4132. Min Act: -0.0001

Data Index: 1435343 (Python Code)

Max Activating Token Index: 356

Text #18

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4084. Min Act: -0.0001

Data Index: 1424574 (Python Code)

Max Activating Token Index: 869

Text #19

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.4083. Min Act: -0.0001

Data Index: 1575267 (Python Code)

Max Activating Token Index: 492