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

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

Neuron 3370 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: 1.2339. Min Range: -1.2339

Max Act: 1.2339. Min Act: -0.0001

Data Index: 960759 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 1.2339. Min Range: -1.2339

Max Act: 1.0829. Min Act: -0.0001

Data Index: 524768 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.9704. Min Act: -0.0001

Data Index: 885127 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.8642. Min Act: -0.0001

Data Index: 842612 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.8552. Min Act: -0.0001

Data Index: 1153155 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.8912. Min Act: -0.0001

Data Index: 255668 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.8583. Min Act: -0.0001

Data Index: 931279 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.8191. Min Act: -0.0001

Data Index: 788201 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.7831. Min Act: -0.0001

Data Index: 543481 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.7608. Min Act: -0.0001

Data Index: 1327340 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.7667. Min Act: -0.0001

Data Index: 805139 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.7669. Min Act: -0.0001

Data Index: 1189799 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.7292. Min Act: -0.0001

Data Index: 1351251 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.7425. Min Act: -0.0001

Data Index: 1210749 (C4 (Web Text))

Max Activating Token Index: 446

Text #14

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.7621. Min Act: -0.0001

Data Index: 709237 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.7448. Min Act: -0.0001

Data Index: 44475 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.7598. Min Act: -0.0001

Data Index: 1132277 (C4 (Web Text))

Max Activating Token Index: 485

Text #17

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.7412. Min Act: -0.0001

Data Index: 674793 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.7137. Min Act: -0.0001

Data Index: 1063283 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 1.2339. Min Range: -1.2339

Max Act: 0.6999. Min Act: -0.0001

Data Index: 1030173 (C4 (Web Text))

Max Activating Token Index: 84