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

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

Neuron 3214 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.5712. Min Act: -0.0001

Data Index: 49676 (C4 (Web Text))

Max Activating Token Index: 589

Text #1

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.5028. Min Act: -0.0001

Data Index: 312193 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.5263. Min Act: -0.0001

Data Index: 317582 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.4911. Min Act: -0.0001

Data Index: 1138146 (C4 (Web Text))

Max Activating Token Index: 17

Text #4

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.4755. Min Act: -0.0001

Data Index: 1084085 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.4615. Min Act: -0.0001

Data Index: 1171759 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.4703. Min Act: -0.0001

Data Index: 548009 (C4 (Web Text))

Max Activating Token Index: 473

Text #7

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.4297. Min Act: -0.0001

Data Index: 1165050 (C4 (Web Text))

Max Activating Token Index: 425

Text #8

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.4863. Min Act: -0.0001

Data Index: 743892 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.4416. Min Act: -0.0001

Data Index: 458630 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.4034. Min Act: -0.0001

Data Index: 1249566 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.3853. Min Act: -0.0001

Data Index: 26414 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.4081. Min Act: -0.0001

Data Index: 507029 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.3821. Min Act: -0.0001

Data Index: 883288 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.3426. Min Act: -0.0001

Data Index: 247779 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.3559. Min Act: -0.0001

Data Index: 535450 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.3435. Min Act: -0.0001

Data Index: 963483 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.3528. Min Act: -0.0001

Data Index: 549345 (C4 (Web Text))

Max Activating Token Index: 407

Text #18

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.3495. Min Act: -0.0001

Data Index: 6306 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 0.5712. Min Range: -0.5712

Max Act: 0.3380. Min Act: -0.0001

Data Index: 422164 (C4 (Web Text))

Max Activating Token Index: 294