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

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

Neuron 2870 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 5.0651. Min Range: -5.0651

Max Act: 5.0651. Min Act: -0.0001

Data Index: 1095863 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 5.0651. Min Range: -5.0651

Max Act: 4.4784. Min Act: -0.0001

Data Index: 1309678 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 5.0651. Min Range: -5.0651

Max Act: 4.5189. Min Act: -0.0001

Data Index: 368349 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 5.0651. Min Range: -5.0651

Max Act: 4.5609. Min Act: -0.0001

Data Index: 582363 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 5.0651. Min Range: -5.0651

Max Act: 4.3757. Min Act: -0.0001

Data Index: 814210 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 5.0651. Min Range: -5.0651

Max Act: 4.0307. Min Act: -0.0001

Data Index: 164140 (C4 (Web Text))

Max Activating Token Index: 535

Text #6

Max Range: 5.0651. Min Range: -5.0651

Max Act: 3.7645. Min Act: -0.0001

Data Index: 1036888 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 5.0651. Min Range: -5.0651

Max Act: 4.2007. Min Act: -0.0001

Data Index: 675525 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 5.0651. Min Range: -5.0651

Max Act: 4.1172. Min Act: -0.0001

Data Index: 967576 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 5.0651. Min Range: -5.0651

Max Act: 3.5672. Min Act: -0.0001

Data Index: 273084 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 5.0651. Min Range: -5.0651

Max Act: 3.4744. Min Act: -0.0001

Data Index: 386922 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 5.0651. Min Range: -5.0651

Max Act: 3.8216. Min Act: -0.0001

Data Index: 98268 (C4 (Web Text))

Max Activating Token Index: 525

Text #12

Max Range: 5.0651. Min Range: -5.0651

Max Act: 3.7322. Min Act: -0.0000

Data Index: 1176280 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 5.0651. Min Range: -5.0651

Max Act: 3.4305. Min Act: -0.0000

Data Index: 10581 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 5.0651. Min Range: -5.0651

Max Act: 3.2298. Min Act: -0.0001

Data Index: 1636337 (Python Code)

Max Activating Token Index: 665

Text #15

Max Range: 5.0651. Min Range: -5.0651

Max Act: 3.2500. Min Act: -0.0001

Data Index: 453055 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 5.0651. Min Range: -5.0651

Max Act: 3.8154. Min Act: -0.0001

Data Index: 1338413 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 5.0651. Min Range: -5.0651

Max Act: 3.9693. Min Act: -0.0001

Data Index: 1179762 (C4 (Web Text))

Max Activating Token Index: 65

Text #18

Max Range: 5.0651. Min Range: -5.0651

Max Act: 3.1620. Min Act: -0.0001

Data Index: 1233965 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 5.0651. Min Range: -5.0651

Max Act: 3.1306. Min Act: -0.0000

Data Index: 1133289 (C4 (Web Text))

Max Activating Token Index: 321