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

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

Neuron 4540 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.7348. Min Act: -0.0000

Data Index: 1267147 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.5562. Min Act: -0.0000

Data Index: 203419 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.4881. Min Act: -0.0000

Data Index: 984639 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.4870. Min Act: -0.0000

Data Index: 940687 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.4735. Min Act: -0.0000

Data Index: 1369911 (Python Code)

Max Activating Token Index: 534

Text #5

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.4634. Min Act: -0.0000

Data Index: 1009540 (C4 (Web Text))

Max Activating Token Index: 330

Text #6

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.4080. Min Act: -0.0000

Data Index: 1505992 (Python Code)

Max Activating Token Index: 139

Text #7

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.4308. Min Act: -0.0000

Data Index: 209617 (C4 (Web Text))

Max Activating Token Index: 661

Text #8

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.4152. Min Act: -0.0000

Data Index: 905904 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.4238. Min Act: -0.0000

Data Index: 186134 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.4003. Min Act: -0.0000

Data Index: 338827 (C4 (Web Text))

Max Activating Token Index: 450

Text #11

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.3960. Min Act: -0.0000

Data Index: 961107 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.3724. Min Act: -0.0000

Data Index: 1199770 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.3761. Min Act: -0.0000

Data Index: 665529 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.3998. Min Act: -0.0000

Data Index: 1122340 (C4 (Web Text))

Max Activating Token Index: 295

Text #15

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.3401. Min Act: -0.0000

Data Index: 790022 (C4 (Web Text))

Max Activating Token Index: 541

Text #16

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.3618. Min Act: -0.0000

Data Index: 1195315 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.3778. Min Act: -0.0000

Data Index: 718280 (C4 (Web Text))

Max Activating Token Index: 508

Text #18

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.3743. Min Act: -0.0000

Data Index: 769155 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 0.7348. Min Range: -0.7348

Max Act: 0.3866. Min Act: -0.0000

Data Index: 1189253 (C4 (Web Text))

Max Activating Token Index: 839