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

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

Neuron 3441 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0947. Min Act: -0.0002

Data Index: 320197 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0767. Min Act: -0.0002

Data Index: 1481567 (Python Code)

Max Activating Token Index: 81

Text #2

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1623064 (Python Code)

Max Activating Token Index: 340

Text #3

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0710. Min Act: -0.0002

Data Index: 1644702 (Python Code)

Max Activating Token Index: 253

Text #4

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0680. Min Act: -0.0002

Data Index: 799363 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0661. Min Act: -0.0002

Data Index: 911037 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0630. Min Act: -0.0002

Data Index: 1613260 (Python Code)

Max Activating Token Index: 299

Text #7

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0621. Min Act: -0.0002

Data Index: 1525257 (Python Code)

Max Activating Token Index: 125

Text #8

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0587. Min Act: -0.0002

Data Index: 649885 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0607. Min Act: -0.0002

Data Index: 1095061 (C4 (Web Text))

Max Activating Token Index: 360

Text #10

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0584. Min Act: -0.0002

Data Index: 1412580 (Python Code)

Max Activating Token Index: 369

Text #11

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0649. Min Act: -0.0002

Data Index: 686247 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0600. Min Act: -0.0002

Data Index: 386361 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0593. Min Act: -0.0002

Data Index: 198829 (C4 (Web Text))

Max Activating Token Index: 591

Text #14

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0565. Min Act: -0.0002

Data Index: 69378 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0605. Min Act: -0.0002

Data Index: 1053989 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0584. Min Act: -0.0002

Data Index: 1033395 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0552. Min Act: -0.0002

Data Index: 289134 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0577. Min Act: -0.0002

Data Index: 1491666 (Python Code)

Max Activating Token Index: 369

Text #19

Max Range: 0.0947. Min Range: -0.0947

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1242389 (C4 (Web Text))

Max Activating Token Index: 972