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

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

Neuron 438 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0154. Min Range: -1.0154

Max Act: 1.0154. Min Act: -0.0001

Data Index: 1299118 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.9349. Min Act: -0.0001

Data Index: 596905 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.8497. Min Act: -0.0001

Data Index: 801800 (C4 (Web Text))

Max Activating Token Index: 968

Text #3

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.8298. Min Act: -0.0001

Data Index: 777495 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.8116. Min Act: -0.0001

Data Index: 61566 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.8316. Min Act: -0.0001

Data Index: 1218069 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.8840. Min Act: -0.0001

Data Index: 1167329 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.8037. Min Act: -0.0001

Data Index: 940207 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.7985. Min Act: -0.0001

Data Index: 36941 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.7332. Min Act: -0.0001

Data Index: 1627005 (Python Code)

Max Activating Token Index: 163

Text #10

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.7834. Min Act: -0.0001

Data Index: 1161333 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.7706. Min Act: -0.0001

Data Index: 9394 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.7554. Min Act: -0.0001

Data Index: 527753 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.7480. Min Act: -0.0001

Data Index: 170101 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.7530. Min Act: -0.0001

Data Index: 757166 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.7678. Min Act: -0.0001

Data Index: 563894 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.6950. Min Act: -0.0001

Data Index: 140528 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.7329. Min Act: -0.0001

Data Index: 310683 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.6630. Min Act: -0.0001

Data Index: 1274771 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 1.0154. Min Range: -1.0154

Max Act: 0.7386. Min Act: -0.0001

Data Index: 402569 (C4 (Web Text))

Max Activating Token Index: 277