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

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

Neuron 1301 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: 4.1255. Min Range: -4.1255

Max Act: 4.1255. Min Act: -0.0000

Data Index: 1518219 (Python Code)

Max Activating Token Index: 880

Text #1

Max Range: 4.1255. Min Range: -4.1255

Max Act: 3.8066. Min Act: -0.0000

Data Index: 1377870 (Python Code)

Max Activating Token Index: 189

Text #2

Max Range: 4.1255. Min Range: -4.1255

Max Act: 3.5783. Min Act: -0.0000

Data Index: 277958 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 4.1255. Min Range: -4.1255

Max Act: 3.1987. Min Act: -0.0000

Data Index: 1592115 (Python Code)

Max Activating Token Index: 347

Text #4

Max Range: 4.1255. Min Range: -4.1255

Max Act: 3.2959. Min Act: -0.0000

Data Index: 1226602 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 4.1255. Min Range: -4.1255

Max Act: 3.1209. Min Act: -0.0000

Data Index: 1477593 (Python Code)

Max Activating Token Index: 77

Text #6

Max Range: 4.1255. Min Range: -4.1255

Max Act: 3.4153. Min Act: -0.0000

Data Index: 1630695 (Python Code)

Max Activating Token Index: 489

Text #7

Max Range: 4.1255. Min Range: -4.1255

Max Act: 3.2241. Min Act: -0.0000

Data Index: 1484606 (Python Code)

Max Activating Token Index: 466

Text #8

Max Range: 4.1255. Min Range: -4.1255

Max Act: 2.9876. Min Act: -0.0000

Data Index: 1573710 (Python Code)

Max Activating Token Index: 40

Text #9

Max Range: 4.1255. Min Range: -4.1255

Max Act: 2.8577. Min Act: -0.0000

Data Index: 754582 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 4.1255. Min Range: -4.1255

Max Act: 2.9101. Min Act: -0.0000

Data Index: 1455621 (Python Code)

Max Activating Token Index: 849

Text #11

Max Range: 4.1255. Min Range: -4.1255

Max Act: 3.2064. Min Act: -0.0000

Data Index: 1535210 (Python Code)

Max Activating Token Index: 879

Text #12

Max Range: 4.1255. Min Range: -4.1255

Max Act: 2.8285. Min Act: -0.0000

Data Index: 1404420 (Python Code)

Max Activating Token Index: 108

Text #13

Max Range: 4.1255. Min Range: -4.1255

Max Act: 2.6734. Min Act: -0.0000

Data Index: 1653237 (Python Code)

Max Activating Token Index: 872

Text #14

Max Range: 4.1255. Min Range: -4.1255

Max Act: 2.6042. Min Act: -0.0000

Data Index: 1627333 (Python Code)

Max Activating Token Index: 294

Text #15

Max Range: 4.1255. Min Range: -4.1255

Max Act: 2.5768. Min Act: -0.0000

Data Index: 1531862 (Python Code)

Max Activating Token Index: 856

Text #16

Max Range: 4.1255. Min Range: -4.1255

Max Act: 2.7732. Min Act: -0.0000

Data Index: 1455423 (Python Code)

Max Activating Token Index: 580

Text #17

Max Range: 4.1255. Min Range: -4.1255

Max Act: 2.8917. Min Act: -0.0000

Data Index: 1608922 (Python Code)

Max Activating Token Index: 425

Text #18

Max Range: 4.1255. Min Range: -4.1255

Max Act: 2.7225. Min Act: -0.0000

Data Index: 1542475 (Python Code)

Max Activating Token Index: 889

Text #19

Max Range: 4.1255. Min Range: -4.1255

Max Act: 2.7182. Min Act: -0.0000

Data Index: 1616156 (Python Code)

Max Activating Token Index: 75