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

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

Neuron 4938 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.4519. Min Act: -0.0000

Data Index: 133708 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3958. Min Act: 0.0000

Data Index: 460178 (C4 (Web Text))

Max Activating Token Index: 442

Text #2

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3797. Min Act: -0.0000

Data Index: 667028 (C4 (Web Text))

Max Activating Token Index: 586

Text #3

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3561. Min Act: 0.0000

Data Index: 794669 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3617. Min Act: -0.0000

Data Index: 794812 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3879. Min Act: -0.0000

Data Index: 1149862 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3817. Min Act: 0.0001

Data Index: 319290 (C4 (Web Text))

Max Activating Token Index: 412

Text #7

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3268. Min Act: -0.0000

Data Index: 42359 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3299. Min Act: -0.0000

Data Index: 507557 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3412. Min Act: -0.0000

Data Index: 1543077 (Python Code)

Max Activating Token Index: 557

Text #10

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.2806. Min Act: -0.0000

Data Index: 1296796 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3125. Min Act: 0.0000

Data Index: 264101 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.2964. Min Act: 0.0000

Data Index: 860630 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3068. Min Act: -0.0000

Data Index: 1315832 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3139. Min Act: -0.0000

Data Index: 1559282 (Python Code)

Max Activating Token Index: 409

Text #15

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3014. Min Act: -0.0000

Data Index: 1392952 (Python Code)

Max Activating Token Index: 505

Text #16

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3073. Min Act: 0.0000

Data Index: 532725 (C4 (Web Text))

Max Activating Token Index: 475

Text #17

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3129. Min Act: -0.0000

Data Index: 409034 (C4 (Web Text))

Max Activating Token Index: 837

Text #18

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.3233. Min Act: -0.0000

Data Index: 703507 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 0.4519. Min Range: -0.4519

Max Act: 0.2955. Min Act: -0.0000

Data Index: 811399 (C4 (Web Text))

Max Activating Token Index: 746