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

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

Neuron 67 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: 0.8307. Min Range: -0.8307

Max Act: 0.8307. Min Act: -0.0000

Data Index: 711987 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.6934. Min Act: -0.0001

Data Index: 1376950 (Python Code)

Max Activating Token Index: 26

Text #2

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.6835. Min Act: -0.0000

Data Index: 296103 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.7134. Min Act: -0.0000

Data Index: 76388 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.6464. Min Act: -0.0000

Data Index: 1208062 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.6448. Min Act: 0.0000

Data Index: 493902 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.6483. Min Act: -0.0001

Data Index: 1412311 (Python Code)

Max Activating Token Index: 706

Text #7

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.5907. Min Act: -0.0000

Data Index: 118436 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.5989. Min Act: -0.0000

Data Index: 379280 (C4 (Web Text))

Max Activating Token Index: 91

Text #9

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.5613. Min Act: -0.0000

Data Index: 561701 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.5629. Min Act: -0.0000

Data Index: 905209 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.6103. Min Act: -0.0000

Data Index: 448011 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.6198. Min Act: -0.0001

Data Index: 1485605 (Python Code)

Max Activating Token Index: 520

Text #13

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.5736. Min Act: -0.0001

Data Index: 1634529 (Python Code)

Max Activating Token Index: 940

Text #14

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.5434. Min Act: -0.0000

Data Index: 798035 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.5766. Min Act: 0.0000

Data Index: 158377 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.5236. Min Act: -0.0000

Data Index: 742107 (C4 (Web Text))

Max Activating Token Index: 854

Text #17

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.5366. Min Act: -0.0000

Data Index: 25862 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.5358. Min Act: -0.0000

Data Index: 775198 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 0.8307. Min Range: -0.8307

Max Act: 0.5463. Min Act: -0.0000

Data Index: 709900 (C4 (Web Text))

Max Activating Token Index: 153