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

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

Neuron 4472 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0242. Min Range: -5.0242

Max Act: 5.0242. Min Act: -0.0000

Data Index: 1006309 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 5.0242. Min Range: -5.0242

Max Act: 4.7822. Min Act: -0.0000

Data Index: 895339 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 5.0242. Min Range: -5.0242

Max Act: 4.4812. Min Act: -0.0000

Data Index: 299577 (C4 (Web Text))

Max Activating Token Index: 885

Text #3

Max Range: 5.0242. Min Range: -5.0242

Max Act: 4.1882. Min Act: -0.0000

Data Index: 156277 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 5.0242. Min Range: -5.0242

Max Act: 4.0993. Min Act: -0.0000

Data Index: 452025 (C4 (Web Text))

Max Activating Token Index: 942

Text #5

Max Range: 5.0242. Min Range: -5.0242

Max Act: 3.9793. Min Act: -0.0000

Data Index: 521095 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 5.0242. Min Range: -5.0242

Max Act: 3.9724. Min Act: -0.0000

Data Index: 1112690 (C4 (Web Text))

Max Activating Token Index: 959

Text #7

Max Range: 5.0242. Min Range: -5.0242

Max Act: 3.9557. Min Act: -0.0000

Data Index: 130227 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 5.0242. Min Range: -5.0242

Max Act: 3.7902. Min Act: -0.0000

Data Index: 685724 (C4 (Web Text))

Max Activating Token Index: 833

Text #9

Max Range: 5.0242. Min Range: -5.0242

Max Act: 3.9215. Min Act: -0.0000

Data Index: 507812 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 5.0242. Min Range: -5.0242

Max Act: 3.9221. Min Act: -0.0000

Data Index: 749717 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 5.0242. Min Range: -5.0242

Max Act: 3.9209. Min Act: -0.0000

Data Index: 673294 (C4 (Web Text))

Max Activating Token Index: 71

Text #12

Max Range: 5.0242. Min Range: -5.0242

Max Act: 3.9043. Min Act: -0.0000

Data Index: 917887 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 5.0242. Min Range: -5.0242

Max Act: 3.6317. Min Act: -0.0000

Data Index: 181355 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 5.0242. Min Range: -5.0242

Max Act: 3.8080. Min Act: -0.0000

Data Index: 286237 (C4 (Web Text))

Max Activating Token Index: 778

Text #15

Max Range: 5.0242. Min Range: -5.0242

Max Act: 3.8048. Min Act: -0.0000

Data Index: 171774 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 5.0242. Min Range: -5.0242

Max Act: 3.7328. Min Act: -0.0000

Data Index: 531178 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 5.0242. Min Range: -5.0242

Max Act: 3.7517. Min Act: -0.0000

Data Index: 731309 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 5.0242. Min Range: -5.0242

Max Act: 3.8936. Min Act: -0.0000

Data Index: 927898 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 5.0242. Min Range: -5.0242

Max Act: 3.5535. Min Act: -0.0000

Data Index: 225300 (C4 (Web Text))

Max Activating Token Index: 241