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

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

Neuron 3559 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.5885. Min Act: -0.0000

Data Index: 1173233 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.5667. Min Act: -0.0001

Data Index: 662509 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.5148. Min Act: -0.0001

Data Index: 669581 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.5005. Min Act: -0.0000

Data Index: 73455 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4540. Min Act: -0.0000

Data Index: 736915 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4541. Min Act: -0.0000

Data Index: 1147091 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4558. Min Act: 0.0001

Data Index: 23202 (C4 (Web Text))

Max Activating Token Index: 56

Text #7

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4498. Min Act: -0.0000

Data Index: 988666 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4452. Min Act: -0.0000

Data Index: 178001 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4191. Min Act: -0.0001

Data Index: 969254 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4188. Min Act: -0.0000

Data Index: 462949 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4215. Min Act: -0.0000

Data Index: 957555 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4184. Min Act: 0.0001

Data Index: 1078477 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4309. Min Act: -0.0001

Data Index: 480970 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4093. Min Act: -0.0000

Data Index: 1187069 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4086. Min Act: -0.0000

Data Index: 302479 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4321. Min Act: -0.0000

Data Index: 902750 (C4 (Web Text))

Max Activating Token Index: 223

Text #17

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.3967. Min Act: -0.0000

Data Index: 59011 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4208. Min Act: -0.0000

Data Index: 1214454 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 0.5885. Min Range: -0.5885

Max Act: 0.4043. Min Act: -0.0001

Data Index: 529312 (C4 (Web Text))

Max Activating Token Index: 47