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

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

Neuron 1525 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: 0.6353. Min Range: -0.6353

Max Act: 0.6353. Min Act: -0.0001

Data Index: 1272838 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5742. Min Act: -0.0001

Data Index: 257970 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5678. Min Act: -0.0001

Data Index: 1114592 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5465. Min Act: -0.0000

Data Index: 506176 (C4 (Web Text))

Max Activating Token Index: 793

Text #4

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5421. Min Act: -0.0000

Data Index: 559625 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.4986. Min Act: -0.0000

Data Index: 612895 (C4 (Web Text))

Max Activating Token Index: 436

Text #6

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5125. Min Act: -0.0000

Data Index: 238465 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5106. Min Act: -0.0000

Data Index: 731225 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.4915. Min Act: -0.0001

Data Index: 559133 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.4895. Min Act: -0.0000

Data Index: 431499 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.5021. Min Act: -0.0000

Data Index: 312658 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.4648. Min Act: -0.0001

Data Index: 105572 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.4664. Min Act: -0.0000

Data Index: 176836 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.4956. Min Act: -0.0000

Data Index: 726591 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.4953. Min Act: -0.0000

Data Index: 58599 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.4917. Min Act: -0.0000

Data Index: 722733 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.4672. Min Act: -0.0000

Data Index: 282218 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.4517. Min Act: -0.0001

Data Index: 1297021 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.4622. Min Act: -0.0001

Data Index: 258386 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 0.6353. Min Range: -0.6353

Max Act: 0.4601. Min Act: -0.0000

Data Index: 92249 (C4 (Web Text))

Max Activating Token Index: 506