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

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

Neuron 3704 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: 0.6930. Min Range: -0.6930

Max Act: 0.6930. Min Act: -0.0001

Data Index: 396873 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.6900. Min Act: -0.0001

Data Index: 474797 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5091. Min Act: -0.0000

Data Index: 1318186 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5197. Min Act: -0.0000

Data Index: 660356 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5157. Min Act: -0.0001

Data Index: 1346004 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.4699. Min Act: -0.0000

Data Index: 475687 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.4345. Min Act: -0.0001

Data Index: 170567 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.4648. Min Act: -0.0001

Data Index: 1170891 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.4359. Min Act: -0.0001

Data Index: 1335586 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.4406. Min Act: -0.0000

Data Index: 792535 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.4221. Min Act: -0.0001

Data Index: 77607 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.4144. Min Act: -0.0001

Data Index: 185937 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.4275. Min Act: -0.0001

Data Index: 170457 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.4088. Min Act: -0.0001

Data Index: 1214229 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.4050. Min Act: -0.0001

Data Index: 774502 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.4027. Min Act: -0.0000

Data Index: 108302 (C4 (Web Text))

Max Activating Token Index: 531

Text #16

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.3843. Min Act: -0.0000

Data Index: 1344801 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.3743. Min Act: -0.0001

Data Index: 650985 (C4 (Web Text))

Max Activating Token Index: 319

Text #18

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.3986. Min Act: -0.0001

Data Index: 525354 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.3972. Min Act: -0.0000

Data Index: 1259403 (C4 (Web Text))

Max Activating Token Index: 177