Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3045 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.6402. Min Act: -0.0000

Data Index: 422744 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.3740. Min Act: -0.0000

Data Index: 1097496 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.4001. Min Act: -0.0000

Data Index: 463551 (C4 (Web Text))

Max Activating Token Index: 1008

Text #3

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.3858. Min Act: -0.0000

Data Index: 450717 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.2994. Min Act: -0.0000

Data Index: 208945 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.3280. Min Act: -0.0000

Data Index: 715781 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.3277. Min Act: -0.0000

Data Index: 994090 (C4 (Web Text))

Max Activating Token Index: 931

Text #7

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.3632. Min Act: -0.0000

Data Index: 982444 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.4045. Min Act: -0.0000

Data Index: 698266 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.2486. Min Act: -0.0000

Data Index: 876627 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.2907. Min Act: -0.0000

Data Index: 1028358 (C4 (Web Text))

Max Activating Token Index: 874

Text #11

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.2523. Min Act: -0.0000

Data Index: 766498 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.2870. Min Act: -0.0000

Data Index: 1007641 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.2789. Min Act: -0.0000

Data Index: 1125245 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.2749. Min Act: -0.0000

Data Index: 361472 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.2723. Min Act: -0.0000

Data Index: 25786 (C4 (Web Text))

Max Activating Token Index: 492

Text #16

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.1642. Min Act: -0.0000

Data Index: 624412 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.2693. Min Act: -0.0000

Data Index: 18730 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.2278. Min Act: -0.0000

Data Index: 1101702 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 1.6402. Min Range: -1.6402

Max Act: 1.2236. Min Act: -0.0000

Data Index: 197838 (C4 (Web Text))

Max Activating Token Index: 646