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

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

Neuron 3067 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6405. Min Range: -4.6405

Max Act: 4.5398. Min Act: -0.0000

Data Index: 570830 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 4.6405. Min Range: -4.6405

Max Act: 4.6405. Min Act: -0.0000

Data Index: 377833 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 4.6405. Min Range: -4.6405

Max Act: 4.3678. Min Act: -0.0000

Data Index: 57171 (C4 (Web Text))

Max Activating Token Index: 516

Text #3

Max Range: 4.6405. Min Range: -4.6405

Max Act: 4.1937. Min Act: -0.0000

Data Index: 772750 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 4.6405. Min Range: -4.6405

Max Act: 4.1815. Min Act: -0.0000

Data Index: 418086 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 4.6405. Min Range: -4.6405

Max Act: 4.1980. Min Act: -0.0000

Data Index: 310537 (C4 (Web Text))

Max Activating Token Index: 199

Text #6

Max Range: 4.6405. Min Range: -4.6405

Max Act: 3.9663. Min Act: -0.0000

Data Index: 378408 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 4.6405. Min Range: -4.6405

Max Act: 3.7592. Min Act: -0.0000

Data Index: 599363 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 4.6405. Min Range: -4.6405

Max Act: 4.0060. Min Act: -0.0000

Data Index: 1126349 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 4.6405. Min Range: -4.6405

Max Act: 3.8519. Min Act: -0.0000

Data Index: 595260 (C4 (Web Text))

Max Activating Token Index: 537

Text #10

Max Range: 4.6405. Min Range: -4.6405

Max Act: 3.8214. Min Act: -0.0000

Data Index: 117034 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 4.6405. Min Range: -4.6405

Max Act: 3.8658. Min Act: -0.0000

Data Index: 744664 (C4 (Web Text))

Max Activating Token Index: 959

Text #12

Max Range: 4.6405. Min Range: -4.6405

Max Act: 3.8491. Min Act: -0.0000

Data Index: 272894 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 4.6405. Min Range: -4.6405

Max Act: 3.4221. Min Act: -0.0000

Data Index: 37871 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 4.6405. Min Range: -4.6405

Max Act: 3.5721. Min Act: -0.0000

Data Index: 636985 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 4.6405. Min Range: -4.6405

Max Act: 3.5501. Min Act: -0.0000

Data Index: 729697 (C4 (Web Text))

Max Activating Token Index: 1007

Text #16

Max Range: 4.6405. Min Range: -4.6405

Max Act: 3.4953. Min Act: -0.0000

Data Index: 452644 (C4 (Web Text))

Max Activating Token Index: 952

Text #17

Max Range: 4.6405. Min Range: -4.6405

Max Act: 3.4960. Min Act: -0.0000

Data Index: 1259073 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 4.6405. Min Range: -4.6405

Max Act: 3.4855. Min Act: -0.0000

Data Index: 967302 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 4.6405. Min Range: -4.6405

Max Act: 3.4322. Min Act: -0.0000

Data Index: 1257486 (C4 (Web Text))

Max Activating Token Index: 657