Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2732 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.7406. Min Act: -0.0000

Data Index: 785447 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.6388. Min Act: -0.0001

Data Index: 1065369 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5970. Min Act: -0.0000

Data Index: 613892 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5732. Min Act: -0.0001

Data Index: 254059 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5669. Min Act: -0.0001

Data Index: 653410 (C4 (Web Text))

Max Activating Token Index: 451

Text #5

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5276. Min Act: -0.0000

Data Index: 552637 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5435. Min Act: -0.0001

Data Index: 775421 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5800. Min Act: -0.0001

Data Index: 604337 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5771. Min Act: -0.0001

Data Index: 1027798 (C4 (Web Text))

Max Activating Token Index: 819

Text #9

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5537. Min Act: -0.0001

Data Index: 357380 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5115. Min Act: -0.0001

Data Index: 1332608 (C4 (Web Text))

Max Activating Token Index: 20

Text #11

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.4924. Min Act: -0.0001

Data Index: 1113638 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.4863. Min Act: -0.0001

Data Index: 1316017 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5009. Min Act: -0.0001

Data Index: 649465 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5177. Min Act: -0.0001

Data Index: 1107917 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5194. Min Act: -0.0001

Data Index: 619261 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5109. Min Act: -0.0001

Data Index: 394413 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.5124. Min Act: -0.0000

Data Index: 1104958 (C4 (Web Text))

Max Activating Token Index: 20

Text #18

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.4979. Min Act: -0.0000

Data Index: 680284 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 0.7406. Min Range: -0.7406

Max Act: 0.4749. Min Act: -0.0001

Data Index: 783381 (C4 (Web Text))

Max Activating Token Index: 668