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

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

Neuron 1949 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: 6.3450. Min Range: -6.3450

Max Act: 6.3450. Min Act: -0.0000

Data Index: 945104 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 6.3450. Min Range: -6.3450

Max Act: 5.1651. Min Act: -0.0000

Data Index: 1569568 (Python Code)

Max Activating Token Index: 31

Text #2

Max Range: 6.3450. Min Range: -6.3450

Max Act: 4.7795. Min Act: -0.0000

Data Index: 1414938 (Python Code)

Max Activating Token Index: 330

Text #3

Max Range: 6.3450. Min Range: -6.3450

Max Act: 4.7632. Min Act: -0.0000

Data Index: 1644173 (Python Code)

Max Activating Token Index: 287

Text #4

Max Range: 6.3450. Min Range: -6.3450

Max Act: 4.9510. Min Act: -0.0000

Data Index: 492742 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 6.3450. Min Range: -6.3450

Max Act: 4.7253. Min Act: -0.0000

Data Index: 567083 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 6.3450. Min Range: -6.3450

Max Act: 4.6663. Min Act: -0.0000

Data Index: 410954 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 6.3450. Min Range: -6.3450

Max Act: 4.5045. Min Act: -0.0000

Data Index: 740667 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 6.3450. Min Range: -6.3450

Max Act: 4.8344. Min Act: -0.0000

Data Index: 381702 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 6.3450. Min Range: -6.3450

Max Act: 4.7809. Min Act: -0.0000

Data Index: 72682 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 6.3450. Min Range: -6.3450

Max Act: 4.5495. Min Act: -0.0000

Data Index: 906134 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 6.3450. Min Range: -6.3450

Max Act: 4.5495. Min Act: -0.0000

Data Index: 692513 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 6.3450. Min Range: -6.3450

Max Act: 4.5462. Min Act: -0.0000

Data Index: 1299923 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 6.3450. Min Range: -6.3450

Max Act: 4.5431. Min Act: -0.0000

Data Index: 928634 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 6.3450. Min Range: -6.3450

Max Act: 4.3150. Min Act: -0.0000

Data Index: 1094985 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 6.3450. Min Range: -6.3450

Max Act: 4.5105. Min Act: -0.0000

Data Index: 1255843 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 6.3450. Min Range: -6.3450

Max Act: 4.2805. Min Act: -0.0000

Data Index: 58918 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 6.3450. Min Range: -6.3450

Max Act: 4.4504. Min Act: -0.0000

Data Index: 798450 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 6.3450. Min Range: -6.3450

Max Act: 4.2702. Min Act: -0.0000

Data Index: 354665 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 6.3450. Min Range: -6.3450

Max Act: 4.4151. Min Act: -0.0000

Data Index: 227755 (C4 (Web Text))

Max Activating Token Index: 657