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

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

Neuron 5965 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6586. Min Act: -0.0001

Data Index: 1380041 (Python Code)

Max Activating Token Index: 162

Text #1

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.7499. Min Act: -0.0001

Data Index: 1635114 (Python Code)

Max Activating Token Index: 652

Text #2

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6873. Min Act: -0.0001

Data Index: 666964 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.7154. Min Act: -0.0001

Data Index: 1543843 (Python Code)

Max Activating Token Index: 984

Text #4

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.7398. Min Act: -0.0000

Data Index: 1626288 (Python Code)

Max Activating Token Index: 846

Text #5

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6784. Min Act: -0.0001

Data Index: 813369 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6409. Min Act: -0.0000

Data Index: 1464950 (Python Code)

Max Activating Token Index: 791

Text #7

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6255. Min Act: -0.0001

Data Index: 1636848 (Python Code)

Max Activating Token Index: 962

Text #8

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.5994. Min Act: -0.0000

Data Index: 1616924 (Python Code)

Max Activating Token Index: 641

Text #9

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6316. Min Act: -0.0001

Data Index: 534040 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6250. Min Act: -0.0001

Data Index: 1533224 (Python Code)

Max Activating Token Index: 876

Text #11

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6450. Min Act: -0.0001

Data Index: 1049301 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6269. Min Act: -0.0001

Data Index: 1366281 (Python Code)

Max Activating Token Index: 947

Text #13

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6441. Min Act: -0.0001

Data Index: 1530693 (Python Code)

Max Activating Token Index: 788

Text #14

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6060. Min Act: -0.0001

Data Index: 1600284 (Python Code)

Max Activating Token Index: 356

Text #15

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.5988. Min Act: -0.0001

Data Index: 1007280 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.5914. Min Act: -0.0001

Data Index: 1392539 (Python Code)

Max Activating Token Index: 215

Text #17

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.6219. Min Act: -0.0001

Data Index: 1363178 (Python Code)

Max Activating Token Index: 267

Text #18

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.5822. Min Act: -0.0001

Data Index: 1419705 (Python Code)

Max Activating Token Index: 600

Text #19

Max Range: 0.7499. Min Range: -0.7499

Max Act: 0.5950. Min Act: -0.0001

Data Index: 1499548 (Python Code)

Max Activating Token Index: 507