Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4220 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.1054. Min Act: -0.0001

Data Index: 1316781 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0884. Min Act: -0.0001

Data Index: 163247 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0634. Min Act: -0.0001

Data Index: 288302 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0894. Min Act: -0.0001

Data Index: 571662 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0789. Min Act: -0.0001

Data Index: 527352 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0865. Min Act: -0.0001

Data Index: 505195 (C4 (Web Text))

Max Activating Token Index: 526

Text #6

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0816. Min Act: -0.0001

Data Index: 693548 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0755. Min Act: -0.0001

Data Index: 899990 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0731. Min Act: -0.0001

Data Index: 582280 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0751. Min Act: -0.0001

Data Index: 1280846 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0772. Min Act: -0.0001

Data Index: 140430 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0983. Min Act: -0.0001

Data Index: 739420 (C4 (Web Text))

Max Activating Token Index: 563

Text #12

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0797. Min Act: -0.0001

Data Index: 137500 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0853. Min Act: -0.0001

Data Index: 1226992 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0767. Min Act: -0.0001

Data Index: 429507 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0818. Min Act: -0.0001

Data Index: 685272 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0967. Min Act: -0.0001

Data Index: 298813 (C4 (Web Text))

Max Activating Token Index: 374

Text #17

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0786. Min Act: -0.0001

Data Index: 320859 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0844. Min Act: -0.0001

Data Index: 773391 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0804. Min Act: -0.0001

Data Index: 465378 (C4 (Web Text))

Max Activating Token Index: 9