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

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

Neuron 583 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.9377. Min Range: -4.9377

Max Act: 4.9377. Min Act: -0.0000

Data Index: 975361 (C4 (Web Text))

Max Activating Token Index: 416

Text #1

Max Range: 4.9377. Min Range: -4.9377

Max Act: 4.8504. Min Act: -0.0000

Data Index: 637247 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 4.9377. Min Range: -4.9377

Max Act: 4.6204. Min Act: -0.0000

Data Index: 326752 (C4 (Web Text))

Max Activating Token Index: 554

Text #3

Max Range: 4.9377. Min Range: -4.9377

Max Act: 4.5390. Min Act: -0.0000

Data Index: 156782 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 4.9377. Min Range: -4.9377

Max Act: 4.6786. Min Act: -0.0000

Data Index: 601278 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 4.9377. Min Range: -4.9377

Max Act: 4.3305. Min Act: -0.0000

Data Index: 1249190 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 4.9377. Min Range: -4.9377

Max Act: 3.8890. Min Act: -0.0000

Data Index: 1256440 (C4 (Web Text))

Max Activating Token Index: 100

Text #7

Max Range: 4.9377. Min Range: -4.9377

Max Act: 3.9070. Min Act: -0.0000

Data Index: 441607 (C4 (Web Text))

Max Activating Token Index: 200

Text #8

Max Range: 4.9377. Min Range: -4.9377

Max Act: 3.4997. Min Act: -0.0000

Data Index: 137583 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 4.9377. Min Range: -4.9377

Max Act: 3.5695. Min Act: -0.0000

Data Index: 1184727 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 4.9377. Min Range: -4.9377

Max Act: 3.6593. Min Act: -0.0001

Data Index: 1280242 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 4.9377. Min Range: -4.9377

Max Act: 3.6404. Min Act: -0.0000

Data Index: 582345 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 4.9377. Min Range: -4.9377

Max Act: 3.4180. Min Act: -0.0000

Data Index: 46032 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 4.9377. Min Range: -4.9377

Max Act: 3.2509. Min Act: -0.0000

Data Index: 1282665 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 4.9377. Min Range: -4.9377

Max Act: 3.3465. Min Act: -0.0000

Data Index: 45917 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 4.9377. Min Range: -4.9377

Max Act: 3.7174. Min Act: -0.0000

Data Index: 817340 (C4 (Web Text))

Max Activating Token Index: 531

Text #16

Max Range: 4.9377. Min Range: -4.9377

Max Act: 3.2316. Min Act: -0.0000

Data Index: 794176 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 4.9377. Min Range: -4.9377

Max Act: 2.7915. Min Act: -0.0000

Data Index: 346706 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 4.9377. Min Range: -4.9377

Max Act: 2.9997. Min Act: -0.0000

Data Index: 868453 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 4.9377. Min Range: -4.9377

Max Act: 3.2430. Min Act: -0.0000

Data Index: 1091013 (C4 (Web Text))

Max Activating Token Index: 786