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

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

Neuron 3750 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: 0.3916. Min Range: -0.3916

Max Act: 0.3916. Min Act: -0.0001

Data Index: 480972 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3551. Min Act: -0.0000

Data Index: 974625 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3015. Min Act: -0.0001

Data Index: 1027705 (C4 (Web Text))

Max Activating Token Index: 1021

Text #3

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3241. Min Act: -0.0001

Data Index: 901703 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3079. Min Act: -0.0000

Data Index: 680908 (C4 (Web Text))

Max Activating Token Index: 705

Text #5

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.2916. Min Act: -0.0000

Data Index: 1274123 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3007. Min Act: -0.0001

Data Index: 1132329 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.2721. Min Act: -0.0000

Data Index: 609588 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.2863. Min Act: -0.0001

Data Index: 39330 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.2836. Min Act: -0.0000

Data Index: 220305 (C4 (Web Text))

Max Activating Token Index: 464

Text #10

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.2769. Min Act: -0.0000

Data Index: 1058794 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.2697. Min Act: -0.0000

Data Index: 226289 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.2671. Min Act: -0.0000

Data Index: 799189 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.2796. Min Act: -0.0000

Data Index: 692763 (C4 (Web Text))

Max Activating Token Index: 576

Text #14

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.2617. Min Act: -0.0001

Data Index: 339099 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.2615. Min Act: -0.0000

Data Index: 1123056 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.2496. Min Act: -0.0000

Data Index: 1356648 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.2463. Min Act: -0.0000

Data Index: 171420 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.2368. Min Act: -0.0001

Data Index: 808130 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.2604. Min Act: -0.0000

Data Index: 1161180 (C4 (Web Text))

Max Activating Token Index: 743