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

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

Neuron 4073 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: 0.5802. Min Range: -0.5802

Max Act: 0.5802. Min Act: -0.0000

Data Index: 410573 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.5802. Min Range: -0.5802

Max Act: 0.4486. Min Act: -0.0001

Data Index: 965987 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 0.5802. Min Range: -0.5802

Max Act: 0.3383. Min Act: -0.0001

Data Index: 1351280 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 0.5802. Min Range: -0.5802

Max Act: 0.3388. Min Act: -0.0001

Data Index: 109066 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 0.5802. Min Range: -0.5802

Max Act: 0.3154. Min Act: -0.0000

Data Index: 269171 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 0.5802. Min Range: -0.5802

Max Act: 0.3262. Min Act: -0.0000

Data Index: 792474 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 0.5802. Min Range: -0.5802

Max Act: 0.3138. Min Act: -0.0000

Data Index: 8737 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 0.5802. Min Range: -0.5802

Max Act: 0.3242. Min Act: -0.0001

Data Index: 820114 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 0.5802. Min Range: -0.5802

Max Act: 0.3002. Min Act: -0.0000

Data Index: 911832 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 0.5802. Min Range: -0.5802

Max Act: 0.3017. Min Act: -0.0000

Data Index: 128953 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 0.5802. Min Range: -0.5802

Max Act: 0.2810. Min Act: -0.0000

Data Index: 1063300 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 0.5802. Min Range: -0.5802

Max Act: 0.2883. Min Act: -0.0000

Data Index: 466120 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 0.5802. Min Range: -0.5802

Max Act: 0.2554. Min Act: -0.0001

Data Index: 399497 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 0.5802. Min Range: -0.5802

Max Act: 0.2693. Min Act: -0.0001

Data Index: 824095 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 0.5802. Min Range: -0.5802

Max Act: 0.2611. Min Act: -0.0000

Data Index: 662205 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 0.5802. Min Range: -0.5802

Max Act: 0.2670. Min Act: -0.0001

Data Index: 324698 (C4 (Web Text))

Max Activating Token Index: 829

Text #16

Max Range: 0.5802. Min Range: -0.5802

Max Act: 0.2738. Min Act: -0.0000

Data Index: 956832 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 0.5802. Min Range: -0.5802

Max Act: 0.2708. Min Act: -0.0000

Data Index: 281063 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 0.5802. Min Range: -0.5802

Max Act: 0.2599. Min Act: -0.0000

Data Index: 758111 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 0.5802. Min Range: -0.5802

Max Act: 0.2491. Min Act: -0.0001

Data Index: 720509 (C4 (Web Text))

Max Activating Token Index: 905