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

Dataset: The Pile

Neuron 4008 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8676. Min Range: -1.8676

Max Act: 1.7250. Min Act: -0.0000

Data Index: 1326983 (The Pile)

Max Activating Token Index: 168

Text #1

Max Range: 1.8676. Min Range: -1.8676

Max Act: 1.8474. Min Act: -0.0000

Data Index: 499733 (The Pile)

Max Activating Token Index: 421

Text #2

Max Range: 1.8676. Min Range: -1.8676

Max Act: 1.8676. Min Act: -0.0000

Data Index: 269323 (The Pile)

Max Activating Token Index: 882

Text #3

Max Range: 1.8676. Min Range: -1.8676

Max Act: 1.7314. Min Act: -0.0000

Data Index: 915434 (The Pile)

Max Activating Token Index: 1020

Text #4

Max Range: 1.8676. Min Range: -1.8676

Max Act: 1.6527. Min Act: -0.0000

Data Index: 1097313 (The Pile)

Max Activating Token Index: 887

Text #5

Max Range: 1.8676. Min Range: -1.8676

Max Act: 1.7079. Min Act: -0.0000

Data Index: 1387267 (The Pile)

Max Activating Token Index: 407

Text #6

Max Range: 1.8676. Min Range: -1.8676

Max Act: 1.6574. Min Act: -0.0000

Data Index: 1551840 (The Pile)

Max Activating Token Index: 89

Text #7

Max Range: 1.8676. Min Range: -1.8676

Max Act: 1.5528. Min Act: -0.0000

Data Index: 1779323 (The Pile)

Max Activating Token Index: 679

Text #8

Max Range: 1.8676. Min Range: -1.8676

Max Act: 1.6421. Min Act: -0.0000

Data Index: 14446 (The Pile)

Max Activating Token Index: 601

Text #9

Max Range: 1.8676. Min Range: -1.8676

Max Act: 1.7141. Min Act: -0.0000

Data Index: 52713 (The Pile)

Max Activating Token Index: 762

Text #10

Max Range: 1.8676. Min Range: -1.8676

Max Act: 1.5254. Min Act: -0.0000

Data Index: 1509153 (The Pile)

Max Activating Token Index: 308

Text #11

Max Range: 1.8676. Min Range: -1.8676

Max Act: 1.7126. Min Act: -0.0000

Data Index: 1702926 (The Pile)

Max Activating Token Index: 76

Text #12

Max Range: 1.8676. Min Range: -1.8676

Max Act: 1.5126. Min Act: -0.0000

Data Index: 1451153 (The Pile)

Max Activating Token Index: 113

Text #13

Max Range: 1.8676. Min Range: -1.8676

Max Act: 1.3536. Min Act: -0.0000

Data Index: 730216 (The Pile)

Max Activating Token Index: 734

Text #14

Max Range: 1.8676. Min Range: -1.8676

Max Act: 1.5264. Min Act: -0.0000

Data Index: 826809 (The Pile)

Max Activating Token Index: 254

Text #15

Max Range: 1.8676. Min Range: -1.8676

Max Act: 1.6380. Min Act: -0.0000

Data Index: 1216063 (The Pile)

Max Activating Token Index: 129

Text #16

Max Range: 1.8676. Min Range: -1.8676

Max Act: 1.5098. Min Act: -0.0000

Data Index: 61695 (The Pile)

Max Activating Token Index: 212

Text #17

Max Range: 1.8676. Min Range: -1.8676

Max Act: 1.6832. Min Act: -0.0000

Data Index: 489276 (The Pile)

Max Activating Token Index: 387

Text #18

Max Range: 1.8676. Min Range: -1.8676

Max Act: 1.5027. Min Act: -0.0000

Data Index: 515700 (The Pile)

Max Activating Token Index: 399

Text #19

Max Range: 1.8676. Min Range: -1.8676

Max Act: 1.4779. Min Act: -0.0000

Data Index: 1963605 (The Pile)

Max Activating Token Index: 269