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

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

Neuron 3773 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6888. Min Range: -1.6888

Max Act: 1.6888. Min Act: -0.0000

Data Index: 1353979 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 1.6888. Min Range: -1.6888

Max Act: 1.3144. Min Act: -0.0000

Data Index: 619654 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 1.6888. Min Range: -1.6888

Max Act: 1.2507. Min Act: -0.0000

Data Index: 249776 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 1.6888. Min Range: -1.6888

Max Act: 1.0948. Min Act: -0.0001

Data Index: 1054368 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 1.6888. Min Range: -1.6888

Max Act: 1.1617. Min Act: -0.0000

Data Index: 1292902 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 1.6888. Min Range: -1.6888

Max Act: 1.2267. Min Act: -0.0001

Data Index: 596584 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 1.6888. Min Range: -1.6888

Max Act: 1.3002. Min Act: -0.0001

Data Index: 584180 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 1.6888. Min Range: -1.6888

Max Act: 1.2948. Min Act: -0.0000

Data Index: 36262 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 1.6888. Min Range: -1.6888

Max Act: 1.1777. Min Act: -0.0001

Data Index: 139920 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 1.6888. Min Range: -1.6888

Max Act: 1.2634. Min Act: -0.0000

Data Index: 69859 (C4 (Web Text))

Max Activating Token Index: 267

Text #10

Max Range: 1.6888. Min Range: -1.6888

Max Act: 1.1372. Min Act: -0.0000

Data Index: 29490 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 1.6888. Min Range: -1.6888

Max Act: 1.2325. Min Act: -0.0000

Data Index: 208558 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 1.6888. Min Range: -1.6888

Max Act: 1.1694. Min Act: -0.0001

Data Index: 994458 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 1.6888. Min Range: -1.6888

Max Act: 1.1983. Min Act: -0.0000

Data Index: 1144578 (C4 (Web Text))

Max Activating Token Index: 15

Text #14

Max Range: 1.6888. Min Range: -1.6888

Max Act: 1.1183. Min Act: -0.0001

Data Index: 270911 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 1.6888. Min Range: -1.6888

Max Act: 1.1779. Min Act: -0.0000

Data Index: 1286906 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 1.6888. Min Range: -1.6888

Max Act: 1.2155. Min Act: -0.0000

Data Index: 784163 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 1.6888. Min Range: -1.6888

Max Act: 1.2817. Min Act: -0.0000

Data Index: 279810 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 1.6888. Min Range: -1.6888

Max Act: 1.0956. Min Act: -0.0001

Data Index: 442943 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 1.6888. Min Range: -1.6888

Max Act: 1.1894. Min Act: -0.0001

Data Index: 1565348 (Python Code)

Max Activating Token Index: 368