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

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

Neuron 2823 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.8968. Min Act: -0.0001

Data Index: 538515 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.7186. Min Act: -0.0001

Data Index: 582279 (C4 (Web Text))

Max Activating Token Index: 827

Text #2

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.7009. Min Act: -0.0001

Data Index: 444150 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6649. Min Act: -0.0001

Data Index: 1087710 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.7705. Min Act: -0.0001

Data Index: 44931 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6673. Min Act: -0.0001

Data Index: 79181 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6707. Min Act: -0.0001

Data Index: 651169 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.7245. Min Act: -0.0001

Data Index: 953665 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6165. Min Act: -0.0001

Data Index: 872680 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6821. Min Act: -0.0001

Data Index: 726155 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6964. Min Act: -0.0001

Data Index: 963173 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6397. Min Act: -0.0001

Data Index: 849651 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6732. Min Act: -0.0001

Data Index: 808133 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6519. Min Act: -0.0001

Data Index: 1075163 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6493. Min Act: -0.0001

Data Index: 386045 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6431. Min Act: -0.0001

Data Index: 1094806 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.5956. Min Act: -0.0001

Data Index: 1045366 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.7177. Min Act: -0.0001

Data Index: 777701 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6774. Min Act: -0.0001

Data Index: 1342348 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 0.8968. Min Range: -0.8968

Max Act: 0.6766. Min Act: -0.0002

Data Index: 971010 (C4 (Web Text))

Max Activating Token Index: 353