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

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

Neuron 4644 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: 2.0997. Min Range: -2.0997

Max Act: 2.0862. Min Act: -0.0001

Data Index: 159167 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 2.0997. Min Range: -2.0997

Max Act: 2.0997. Min Act: -0.0000

Data Index: 1490724 (Python Code)

Max Activating Token Index: 507

Text #2

Max Range: 2.0997. Min Range: -2.0997

Max Act: 1.8853. Min Act: -0.0000

Data Index: 187876 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 2.0997. Min Range: -2.0997

Max Act: 1.9482. Min Act: -0.0001

Data Index: 690061 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 2.0997. Min Range: -2.0997

Max Act: 1.9000. Min Act: -0.0000

Data Index: 1215696 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 2.0997. Min Range: -2.0997

Max Act: 1.7598. Min Act: -0.0000

Data Index: 829071 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 2.0997. Min Range: -2.0997

Max Act: 1.9482. Min Act: -0.0001

Data Index: 266688 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 2.0997. Min Range: -2.0997

Max Act: 1.8335. Min Act: -0.0001

Data Index: 470568 (C4 (Web Text))

Max Activating Token Index: 479

Text #8

Max Range: 2.0997. Min Range: -2.0997

Max Act: 1.7464. Min Act: -0.0001

Data Index: 818050 (C4 (Web Text))

Max Activating Token Index: 180

Text #9

Max Range: 2.0997. Min Range: -2.0997

Max Act: 1.8276. Min Act: -0.0000

Data Index: 266612 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 2.0997. Min Range: -2.0997

Max Act: 1.8292. Min Act: -0.0000

Data Index: 1299116 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 2.0997. Min Range: -2.0997

Max Act: 1.6404. Min Act: -0.0000

Data Index: 165368 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 2.0997. Min Range: -2.0997

Max Act: 1.6299. Min Act: -0.0000

Data Index: 1269086 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 2.0997. Min Range: -2.0997

Max Act: 1.6307. Min Act: -0.0000

Data Index: 312314 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 2.0997. Min Range: -2.0997

Max Act: 1.7823. Min Act: -0.0001

Data Index: 1554414 (Python Code)

Max Activating Token Index: 301

Text #15

Max Range: 2.0997. Min Range: -2.0997

Max Act: 1.5719. Min Act: -0.0000

Data Index: 1609486 (Python Code)

Max Activating Token Index: 166

Text #16

Max Range: 2.0997. Min Range: -2.0997

Max Act: 1.5503. Min Act: -0.0000

Data Index: 835192 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 2.0997. Min Range: -2.0997

Max Act: 1.6470. Min Act: -0.0000

Data Index: 1043333 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 2.0997. Min Range: -2.0997

Max Act: 1.6442. Min Act: -0.0001

Data Index: 1570679 (Python Code)

Max Activating Token Index: 61

Text #19

Max Range: 2.0997. Min Range: -2.0997

Max Act: 1.6279. Min Act: -0.0001

Data Index: 46218 (C4 (Web Text))

Max Activating Token Index: 553