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

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

Neuron 252 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.9435. Min Act: -0.0000

Data Index: 728220 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.2725. Min Act: -0.0000

Data Index: 1618965 (Python Code)

Max Activating Token Index: 364

Text #2

Max Range: 3.9435. Min Range: -3.9435

Max Act: 3.3090. Min Act: -0.0000

Data Index: 1465173 (Python Code)

Max Activating Token Index: 984

Text #3

Max Range: 3.9435. Min Range: -3.9435

Max Act: 2.9654. Min Act: -0.0000

Data Index: 1502361 (Python Code)

Max Activating Token Index: 527

Text #4

Max Range: 3.9435. Min Range: -3.9435

Max Act: 2.8094. Min Act: -0.0000

Data Index: 1610220 (Python Code)

Max Activating Token Index: 70

Text #5

Max Range: 3.9435. Min Range: -3.9435

Max Act: 2.8773. Min Act: -0.0000

Data Index: 1655544 (Python Code)

Max Activating Token Index: 373

Text #6

Max Range: 3.9435. Min Range: -3.9435

Max Act: 2.8911. Min Act: -0.0000

Data Index: 1488183 (Python Code)

Max Activating Token Index: 380

Text #7

Max Range: 3.9435. Min Range: -3.9435

Max Act: 2.6799. Min Act: -0.0000

Data Index: 65286 (C4 (Web Text))

Max Activating Token Index: 358

Text #8

Max Range: 3.9435. Min Range: -3.9435

Max Act: 2.8403. Min Act: -0.0000

Data Index: 1648 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 3.9435. Min Range: -3.9435

Max Act: 2.6640. Min Act: -0.0000

Data Index: 612162 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 3.9435. Min Range: -3.9435

Max Act: 2.2647. Min Act: -0.0000

Data Index: 1025417 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 3.9435. Min Range: -3.9435

Max Act: 2.7446. Min Act: -0.0000

Data Index: 334234 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 3.9435. Min Range: -3.9435

Max Act: 2.5587. Min Act: -0.0000

Data Index: 1631371 (Python Code)

Max Activating Token Index: 351

Text #13

Max Range: 3.9435. Min Range: -3.9435

Max Act: 2.6849. Min Act: -0.0000

Data Index: 1621647 (Python Code)

Max Activating Token Index: 69

Text #14

Max Range: 3.9435. Min Range: -3.9435

Max Act: 2.6892. Min Act: -0.0000

Data Index: 1601007 (Python Code)

Max Activating Token Index: 173

Text #15

Max Range: 3.9435. Min Range: -3.9435

Max Act: 2.8341. Min Act: -0.0000

Data Index: 1270068 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 3.9435. Min Range: -3.9435

Max Act: 2.6268. Min Act: -0.0000

Data Index: 1599690 (Python Code)

Max Activating Token Index: 691

Text #17

Max Range: 3.9435. Min Range: -3.9435

Max Act: 2.4836. Min Act: -0.0000

Data Index: 1586344 (Python Code)

Max Activating Token Index: 164

Text #18

Max Range: 3.9435. Min Range: -3.9435

Max Act: 2.7384. Min Act: -0.0000

Data Index: 383447 (C4 (Web Text))

Max Activating Token Index: 227

Text #19

Max Range: 3.9435. Min Range: -3.9435

Max Act: 2.4226. Min Act: -0.0000

Data Index: 112046 (C4 (Web Text))

Max Activating Token Index: 315