Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4372 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8858. Min Range: -1.8858

Max Act: 1.8858. Min Act: -0.0000

Data Index: 202355 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 1.8858. Min Range: -1.8858

Max Act: 1.7856. Min Act: -0.0000

Data Index: 256519 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 1.8858. Min Range: -1.8858

Max Act: 1.6239. Min Act: -0.0000

Data Index: 280924 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 1.8858. Min Range: -1.8858

Max Act: 1.4810. Min Act: -0.0001

Data Index: 185808 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 1.8858. Min Range: -1.8858

Max Act: 1.4918. Min Act: -0.0001

Data Index: 394113 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 1.8858. Min Range: -1.8858

Max Act: 1.4199. Min Act: -0.0000

Data Index: 1269596 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 1.8858. Min Range: -1.8858

Max Act: 1.4255. Min Act: -0.0000

Data Index: 974681 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 1.8858. Min Range: -1.8858

Max Act: 1.4493. Min Act: -0.0000

Data Index: 777088 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 1.8858. Min Range: -1.8858

Max Act: 1.2450. Min Act: -0.0000

Data Index: 840581 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 1.8858. Min Range: -1.8858

Max Act: 1.3334. Min Act: -0.0000

Data Index: 884213 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 1.8858. Min Range: -1.8858

Max Act: 1.3316. Min Act: -0.0000

Data Index: 407764 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 1.8858. Min Range: -1.8858

Max Act: 1.3182. Min Act: -0.0000

Data Index: 1278878 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 1.8858. Min Range: -1.8858

Max Act: 1.3070. Min Act: -0.0000

Data Index: 628200 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 1.8858. Min Range: -1.8858

Max Act: 1.2646. Min Act: -0.0000

Data Index: 855604 (C4 (Web Text))

Max Activating Token Index: 920

Text #14

Max Range: 1.8858. Min Range: -1.8858

Max Act: 1.1943. Min Act: -0.0000

Data Index: 159907 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 1.8858. Min Range: -1.8858

Max Act: 1.2871. Min Act: -0.0000

Data Index: 1070022 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 1.8858. Min Range: -1.8858

Max Act: 1.1934. Min Act: -0.0000

Data Index: 16206 (C4 (Web Text))

Max Activating Token Index: 669

Text #17

Max Range: 1.8858. Min Range: -1.8858

Max Act: 1.2727. Min Act: -0.0000

Data Index: 1035835 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 1.8858. Min Range: -1.8858

Max Act: 1.1089. Min Act: -0.0000

Data Index: 439699 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 1.8858. Min Range: -1.8858

Max Act: 1.1773. Min Act: -0.0000

Data Index: 221589 (C4 (Web Text))

Max Activating Token Index: 876