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

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

Neuron 317 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: 0.7890. Min Range: -0.7890

Max Act: 0.7890. Min Act: -0.0002

Data Index: 1298957 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.4694. Min Act: -0.0002

Data Index: 273026 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.4210. Min Act: -0.0001

Data Index: 673266 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.3970. Min Act: -0.0001

Data Index: 1087616 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.4088. Min Act: -0.0002

Data Index: 1271941 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.3693. Min Act: -0.0002

Data Index: 241162 (C4 (Web Text))

Max Activating Token Index: 620

Text #6

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.3646. Min Act: -0.0002

Data Index: 250132 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.3259. Min Act: -0.0001

Data Index: 404889 (C4 (Web Text))

Max Activating Token Index: 931

Text #8

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.3493. Min Act: -0.0002

Data Index: 30547 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.3059. Min Act: -0.0001

Data Index: 425778 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.3385. Min Act: -0.0001

Data Index: 1488417 (Python Code)

Max Activating Token Index: 51

Text #11

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.3426. Min Act: -0.0001

Data Index: 1158472 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.3365. Min Act: -0.0001

Data Index: 1609111 (Python Code)

Max Activating Token Index: 855

Text #13

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.3248. Min Act: -0.0001

Data Index: 1256940 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.3348. Min Act: -0.0001

Data Index: 249066 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.3568. Min Act: -0.0002

Data Index: 913140 (C4 (Web Text))

Max Activating Token Index: 212

Text #16

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.3535. Min Act: -0.0002

Data Index: 305184 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.3430. Min Act: -0.0001

Data Index: 1024803 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.3412. Min Act: -0.0001

Data Index: 1585482 (Python Code)

Max Activating Token Index: 925

Text #19

Max Range: 0.7890. Min Range: -0.7890

Max Act: 0.3285. Min Act: -0.0001

Data Index: 1432692 (Python Code)

Max Activating Token Index: 255