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

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

Neuron 855 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: 0.7230. Min Range: -0.7230

Max Act: 0.7064. Min Act: -0.0001

Data Index: 1084072 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.7230. Min Act: -0.0001

Data Index: 1095120 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.6136. Min Act: -0.0001

Data Index: 76391 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.5760. Min Act: -0.0001

Data Index: 491890 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.5931. Min Act: -0.0001

Data Index: 474179 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.6056. Min Act: -0.0001

Data Index: 272431 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.5547. Min Act: -0.0001

Data Index: 872749 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.5737. Min Act: -0.0001

Data Index: 1165823 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.5905. Min Act: -0.0001

Data Index: 1256928 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.5073. Min Act: -0.0002

Data Index: 1234341 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.5689. Min Act: -0.0001

Data Index: 751493 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.6040. Min Act: -0.0001

Data Index: 649217 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.5552. Min Act: -0.0001

Data Index: 238576 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.4855. Min Act: -0.0001

Data Index: 1182686 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.5436. Min Act: -0.0001

Data Index: 655809 (C4 (Web Text))

Max Activating Token Index: 952

Text #15

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.4752. Min Act: -0.0001

Data Index: 876576 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.4884. Min Act: -0.0001

Data Index: 1025510 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.5411. Min Act: -0.0001

Data Index: 761351 (C4 (Web Text))

Max Activating Token Index: 448

Text #18

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.5622. Min Act: -0.0001

Data Index: 518687 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.5510. Min Act: -0.0001

Data Index: 659153 (C4 (Web Text))

Max Activating Token Index: 586