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

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

Neuron 2538 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: 0.6098. Min Range: -0.6098

Max Act: 0.6098. Min Act: -0.0001

Data Index: 1103861 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5732. Min Act: -0.0001

Data Index: 1085049 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5330. Min Act: -0.0001

Data Index: 901042 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5530. Min Act: -0.0001

Data Index: 377335 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5326. Min Act: -0.0001

Data Index: 164774 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5122. Min Act: -0.0001

Data Index: 1141991 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4997. Min Act: -0.0001

Data Index: 891668 (C4 (Web Text))

Max Activating Token Index: 989

Text #7

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.5131. Min Act: -0.0001

Data Index: 1088801 (C4 (Web Text))

Max Activating Token Index: 194

Text #8

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4622. Min Act: -0.0001

Data Index: 448196 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4883. Min Act: -0.0001

Data Index: 389701 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4731. Min Act: -0.0001

Data Index: 1232417 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4702. Min Act: -0.0001

Data Index: 1012238 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4844. Min Act: -0.0001

Data Index: 720277 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4574. Min Act: -0.0001

Data Index: 57464 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4661. Min Act: -0.0001

Data Index: 798973 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4686. Min Act: -0.0001

Data Index: 108079 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4605. Min Act: -0.0001

Data Index: 546503 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4382. Min Act: -0.0001

Data Index: 49678 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4674. Min Act: -0.0001

Data Index: 913380 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 0.6098. Min Range: -0.6098

Max Act: 0.4635. Min Act: -0.0001

Data Index: 393378 (C4 (Web Text))

Max Activating Token Index: 910