Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2074 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.3127. Min Range: -3.3127

Max Act: 3.3127. Min Act: -0.0000

Data Index: 133418 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 3.3127. Min Range: -3.3127

Max Act: 2.9861. Min Act: -0.0000

Data Index: 686222 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 3.3127. Min Range: -3.3127

Max Act: 3.0590. Min Act: -0.0000

Data Index: 71483 (C4 (Web Text))

Max Activating Token Index: 705

Text #3

Max Range: 3.3127. Min Range: -3.3127

Max Act: 3.0984. Min Act: -0.0000

Data Index: 899875 (C4 (Web Text))

Max Activating Token Index: 267

Text #4

Max Range: 3.3127. Min Range: -3.3127

Max Act: 2.7604. Min Act: -0.0000

Data Index: 557140 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 3.3127. Min Range: -3.3127

Max Act: 3.0177. Min Act: -0.0000

Data Index: 267806 (C4 (Web Text))

Max Activating Token Index: 464

Text #6

Max Range: 3.3127. Min Range: -3.3127

Max Act: 2.7347. Min Act: -0.0000

Data Index: 964320 (C4 (Web Text))

Max Activating Token Index: 845

Text #7

Max Range: 3.3127. Min Range: -3.3127

Max Act: 2.4082. Min Act: -0.0000

Data Index: 667147 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 3.3127. Min Range: -3.3127

Max Act: 2.4686. Min Act: -0.0000

Data Index: 291022 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 3.3127. Min Range: -3.3127

Max Act: 2.5279. Min Act: -0.0000

Data Index: 553589 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 3.3127. Min Range: -3.3127

Max Act: 2.4899. Min Act: -0.0000

Data Index: 36828 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 3.3127. Min Range: -3.3127

Max Act: 2.3624. Min Act: -0.0000

Data Index: 268160 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 3.3127. Min Range: -3.3127

Max Act: 2.3985. Min Act: -0.0000

Data Index: 914028 (C4 (Web Text))

Max Activating Token Index: 308

Text #13

Max Range: 3.3127. Min Range: -3.3127

Max Act: 2.3914. Min Act: -0.0000

Data Index: 1020007 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 3.3127. Min Range: -3.3127

Max Act: 2.5057. Min Act: -0.0000

Data Index: 635355 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 3.3127. Min Range: -3.3127

Max Act: 2.4684. Min Act: -0.0000

Data Index: 1164530 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 3.3127. Min Range: -3.3127

Max Act: 2.5888. Min Act: -0.0001

Data Index: 1189077 (C4 (Web Text))

Max Activating Token Index: 367

Text #17

Max Range: 3.3127. Min Range: -3.3127

Max Act: 2.4430. Min Act: -0.0000

Data Index: 1122188 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 3.3127. Min Range: -3.3127

Max Act: 2.3113. Min Act: -0.0000

Data Index: 1095138 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 3.3127. Min Range: -3.3127

Max Act: 2.1585. Min Act: -0.0000

Data Index: 251510 (C4 (Web Text))

Max Activating Token Index: 851