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

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

Neuron 1944 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.4962. Min Act: -0.0001

Data Index: 898097 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.4970. Min Act: -0.0001

Data Index: 633290 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.4841. Min Act: -0.0001

Data Index: 736957 (C4 (Web Text))

Max Activating Token Index: 901

Text #3

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.4860. Min Act: -0.0000

Data Index: 894124 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.4109. Min Act: -0.0001

Data Index: 390967 (C4 (Web Text))

Max Activating Token Index: 568

Text #5

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.4830. Min Act: -0.0000

Data Index: 347588 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.4513. Min Act: -0.0000

Data Index: 234816 (C4 (Web Text))

Max Activating Token Index: 748

Text #7

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.4604. Min Act: -0.0001

Data Index: 1008413 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.4484. Min Act: -0.0000

Data Index: 1327193 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.4520. Min Act: -0.0001

Data Index: 624179 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.4107. Min Act: -0.0000

Data Index: 455867 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.4191. Min Act: -0.0000

Data Index: 869541 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.4322. Min Act: -0.0000

Data Index: 1162503 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.4341. Min Act: -0.0001

Data Index: 903875 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.4259. Min Act: -0.0000

Data Index: 1077025 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.4364. Min Act: -0.0000

Data Index: 7742 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.4308. Min Act: -0.0000

Data Index: 470387 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.4267. Min Act: -0.0000

Data Index: 431268 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.4024. Min Act: -0.0000

Data Index: 1261400 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 0.4970. Min Range: -0.4970

Max Act: 0.4314. Min Act: -0.0001

Data Index: 608812 (C4 (Web Text))

Max Activating Token Index: 803