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

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

Neuron 2063 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7786. Min Range: -3.7786

Max Act: 3.7786. Min Act: -0.0000

Data Index: 629663 (C4 (Web Text))

Max Activating Token Index: 917

Text #1

Max Range: 3.7786. Min Range: -3.7786

Max Act: 3.3879. Min Act: -0.0000

Data Index: 1205558 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 3.7786. Min Range: -3.7786

Max Act: 3.2715. Min Act: -0.0000

Data Index: 127144 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 3.7786. Min Range: -3.7786

Max Act: 3.0540. Min Act: -0.0000

Data Index: 1151039 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 3.7786. Min Range: -3.7786

Max Act: 3.0169. Min Act: -0.0000

Data Index: 643871 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 3.7786. Min Range: -3.7786

Max Act: 2.8707. Min Act: -0.0000

Data Index: 671988 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 3.7786. Min Range: -3.7786

Max Act: 2.7173. Min Act: -0.0000

Data Index: 911962 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 3.7786. Min Range: -3.7786

Max Act: 2.8080. Min Act: -0.0000

Data Index: 1308077 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 3.7786. Min Range: -3.7786

Max Act: 2.8635. Min Act: -0.0000

Data Index: 1175552 (C4 (Web Text))

Max Activating Token Index: 559

Text #9

Max Range: 3.7786. Min Range: -3.7786

Max Act: 2.6716. Min Act: -0.0000

Data Index: 145146 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 3.7786. Min Range: -3.7786

Max Act: 2.5633. Min Act: -0.0000

Data Index: 348709 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 3.7786. Min Range: -3.7786

Max Act: 2.3356. Min Act: -0.0000

Data Index: 689887 (C4 (Web Text))

Max Activating Token Index: 135

Text #12

Max Range: 3.7786. Min Range: -3.7786

Max Act: 2.3199. Min Act: -0.0000

Data Index: 526640 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 3.7786. Min Range: -3.7786

Max Act: 2.2967. Min Act: -0.0000

Data Index: 1191350 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 3.7786. Min Range: -3.7786

Max Act: 2.1457. Min Act: -0.0000

Data Index: 89814 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 3.7786. Min Range: -3.7786

Max Act: 2.2006. Min Act: -0.0000

Data Index: 457207 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 3.7786. Min Range: -3.7786

Max Act: 2.0738. Min Act: -0.0000

Data Index: 824363 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 3.7786. Min Range: -3.7786

Max Act: 2.0613. Min Act: -0.0000

Data Index: 481267 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 3.7786. Min Range: -3.7786

Max Act: 2.2881. Min Act: -0.0000

Data Index: 321925 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 3.7786. Min Range: -3.7786

Max Act: 2.1328. Min Act: -0.0000

Data Index: 156009 (C4 (Web Text))

Max Activating Token Index: 249