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

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

Neuron 2040 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.4475. Min Act: -0.0000

Data Index: 878225 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.3745. Min Act: -0.0000

Data Index: 318878 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.3453. Min Act: -0.0000

Data Index: 814954 (C4 (Web Text))

Max Activating Token Index: 987

Text #3

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.3275. Min Act: -0.0000

Data Index: 978678 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.3270. Min Act: -0.0000

Data Index: 686948 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.3206. Min Act: -0.0001

Data Index: 648121 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.3085. Min Act: -0.0001

Data Index: 608024 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.3177. Min Act: -0.0000

Data Index: 424646 (C4 (Web Text))

Max Activating Token Index: 780

Text #8

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.2942. Min Act: -0.0001

Data Index: 346887 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.2651. Min Act: -0.0000

Data Index: 354272 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.2870. Min Act: -0.0001

Data Index: 769132 (C4 (Web Text))

Max Activating Token Index: 483

Text #11

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.2901. Min Act: -0.0001

Data Index: 456680 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.2655. Min Act: -0.0000

Data Index: 1304796 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.2854. Min Act: -0.0001

Data Index: 192881 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.2643. Min Act: -0.0000

Data Index: 523158 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.2677. Min Act: -0.0000

Data Index: 777906 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.2535. Min Act: -0.0001

Data Index: 264480 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.2674. Min Act: -0.0000

Data Index: 1046228 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.2936. Min Act: -0.0000

Data Index: 553005 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 0.4475. Min Range: -0.4475

Max Act: 0.2745. Min Act: -0.0000

Data Index: 740448 (C4 (Web Text))

Max Activating Token Index: 597