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

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

Neuron 3430 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5583. Min Act: -0.0001

Data Index: 1268397 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5894. Min Act: -0.0001

Data Index: 1401770 (Python Code)

Max Activating Token Index: 493

Text #2

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5864. Min Act: -0.0001

Data Index: 35028 (C4 (Web Text))

Max Activating Token Index: 716

Text #3

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5960. Min Act: -0.0000

Data Index: 64626 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4895. Min Act: -0.0001

Data Index: 1514319 (Python Code)

Max Activating Token Index: 738

Text #5

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5190. Min Act: -0.0001

Data Index: 924662 (C4 (Web Text))

Max Activating Token Index: 210

Text #6

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5102. Min Act: -0.0000

Data Index: 399224 (C4 (Web Text))

Max Activating Token Index: 883

Text #7

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5008. Min Act: -0.0001

Data Index: 1082981 (C4 (Web Text))

Max Activating Token Index: 305

Text #8

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4589. Min Act: -0.0001

Data Index: 860405 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4738. Min Act: -0.0001

Data Index: 424773 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4876. Min Act: -0.0000

Data Index: 850000 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4557. Min Act: -0.0001

Data Index: 1180622 (C4 (Web Text))

Max Activating Token Index: 959

Text #12

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4673. Min Act: -0.0000

Data Index: 628195 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4845. Min Act: -0.0001

Data Index: 225518 (C4 (Web Text))

Max Activating Token Index: 390

Text #14

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4702. Min Act: -0.0001

Data Index: 927355 (C4 (Web Text))

Max Activating Token Index: 477

Text #15

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4654. Min Act: -0.0001

Data Index: 409065 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4760. Min Act: -0.0001

Data Index: 251694 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4461. Min Act: -0.0001

Data Index: 1030770 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4550. Min Act: -0.0001

Data Index: 228340 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4540. Min Act: -0.0001

Data Index: 1222900 (C4 (Web Text))

Max Activating Token Index: 791