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

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

Neuron 4196 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.6399. Min Act: -0.0000

Data Index: 937567 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.6291. Min Act: -0.0000

Data Index: 211411 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.5965. Min Act: -0.0000

Data Index: 80117 (C4 (Web Text))

Max Activating Token Index: 851

Text #3

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.6061. Min Act: -0.0000

Data Index: 500780 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.5837. Min Act: -0.0000

Data Index: 925118 (C4 (Web Text))

Max Activating Token Index: 965

Text #5

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.5642. Min Act: -0.0001

Data Index: 1600721 (Python Code)

Max Activating Token Index: 756

Text #6

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.5699. Min Act: -0.0000

Data Index: 139449 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.5494. Min Act: -0.0000

Data Index: 610240 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.5672. Min Act: -0.0000

Data Index: 1175353 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.5797. Min Act: -0.0000

Data Index: 167936 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.5310. Min Act: -0.0000

Data Index: 1233629 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.5472. Min Act: -0.0000

Data Index: 707582 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.5491. Min Act: -0.0000

Data Index: 635327 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.5508. Min Act: -0.0000

Data Index: 1427832 (Python Code)

Max Activating Token Index: 202

Text #14

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.5313. Min Act: -0.0000

Data Index: 1599832 (Python Code)

Max Activating Token Index: 464

Text #15

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.4965. Min Act: -0.0000

Data Index: 1130214 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.5030. Min Act: -0.0000

Data Index: 593058 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.4970. Min Act: -0.0000

Data Index: 1167015 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.5015. Min Act: -0.0000

Data Index: 394609 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 0.6399. Min Range: -0.6399

Max Act: 0.5118. Min Act: -0.0000

Data Index: 224164 (C4 (Web Text))

Max Activating Token Index: 690