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

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

Neuron 65 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8363. Min Range: -2.8363

Max Act: 2.8363. Min Act: -0.0000

Data Index: 581473 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 2.8363. Min Range: -2.8363

Max Act: 2.3410. Min Act: -0.0000

Data Index: 937782 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 2.8363. Min Range: -2.8363

Max Act: 2.4429. Min Act: -0.0000

Data Index: 739167 (C4 (Web Text))

Max Activating Token Index: 888

Text #3

Max Range: 2.8363. Min Range: -2.8363

Max Act: 2.3225. Min Act: -0.0000

Data Index: 701000 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 2.8363. Min Range: -2.8363

Max Act: 2.2971. Min Act: -0.0000

Data Index: 462845 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 2.8363. Min Range: -2.8363

Max Act: 2.0289. Min Act: -0.0000

Data Index: 1106964 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 2.8363. Min Range: -2.8363

Max Act: 2.0123. Min Act: -0.0000

Data Index: 615328 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 2.8363. Min Range: -2.8363

Max Act: 1.9832. Min Act: -0.0000

Data Index: 1153825 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 2.8363. Min Range: -2.8363

Max Act: 1.8547. Min Act: -0.0000

Data Index: 915435 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 2.8363. Min Range: -2.8363

Max Act: 1.8699. Min Act: -0.0000

Data Index: 996934 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 2.8363. Min Range: -2.8363

Max Act: 1.8725. Min Act: -0.0000

Data Index: 697020 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 2.8363. Min Range: -2.8363

Max Act: 1.7182. Min Act: -0.0000

Data Index: 1268898 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 2.8363. Min Range: -2.8363

Max Act: 1.8005. Min Act: -0.0000

Data Index: 744910 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 2.8363. Min Range: -2.8363

Max Act: 1.9238. Min Act: -0.0000

Data Index: 276985 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 2.8363. Min Range: -2.8363

Max Act: 1.7017. Min Act: -0.0000

Data Index: 1076273 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 2.8363. Min Range: -2.8363

Max Act: 1.7388. Min Act: -0.0000

Data Index: 101823 (C4 (Web Text))

Max Activating Token Index: 1010

Text #16

Max Range: 2.8363. Min Range: -2.8363

Max Act: 1.6998. Min Act: -0.0000

Data Index: 423270 (C4 (Web Text))

Max Activating Token Index: 953

Text #17

Max Range: 2.8363. Min Range: -2.8363

Max Act: 1.7633. Min Act: -0.0000

Data Index: 1073227 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 2.8363. Min Range: -2.8363

Max Act: 1.9484. Min Act: -0.0000

Data Index: 960752 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 2.8363. Min Range: -2.8363

Max Act: 1.9733. Min Act: -0.0000

Data Index: 1280531 (C4 (Web Text))

Max Activating Token Index: 704