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

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

Neuron 2311 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.8949. Min Act: -0.0002

Data Index: 339756 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.8769. Min Act: -0.0002

Data Index: 1159331 (C4 (Web Text))

Max Activating Token Index: 861

Text #2

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.9041. Min Act: -0.0001

Data Index: 712305 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.8703. Min Act: -0.0002

Data Index: 456486 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.8508. Min Act: -0.0002

Data Index: 1347702 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.8256. Min Act: -0.0001

Data Index: 905873 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7819. Min Act: -0.0002

Data Index: 566397 (C4 (Web Text))

Max Activating Token Index: 729

Text #7

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.8060. Min Act: -0.0001

Data Index: 1049074 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.8411. Min Act: -0.0002

Data Index: 230542 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7577. Min Act: -0.0001

Data Index: 937065 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7992. Min Act: -0.0002

Data Index: 841051 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7814. Min Act: -0.0002

Data Index: 861226 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7214. Min Act: -0.0001

Data Index: 492360 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7461. Min Act: -0.0002

Data Index: 418575 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.6980. Min Act: -0.0001

Data Index: 1099377 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7350. Min Act: -0.0002

Data Index: 1092996 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7167. Min Act: -0.0002

Data Index: 241331 (C4 (Web Text))

Max Activating Token Index: 529

Text #17

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.6861. Min Act: -0.0002

Data Index: 941620 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.6785. Min Act: -0.0001

Data Index: 298647 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.9041. Min Range: -0.9041

Max Act: 0.7142. Min Act: -0.0002

Data Index: 81351 (C4 (Web Text))

Max Activating Token Index: 101