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

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

Neuron 1910 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.5952. Min Act: -0.0000

Data Index: 753136 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.4039. Min Act: -0.0000

Data Index: 310472 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.3724. Min Act: -0.0000

Data Index: 109914 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.3163. Min Act: -0.0000

Data Index: 249088 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.3139. Min Act: -0.0000

Data Index: 1122936 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.2985. Min Act: -0.0000

Data Index: 656509 (C4 (Web Text))

Max Activating Token Index: 133

Text #6

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.3282. Min Act: -0.0000

Data Index: 640349 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.2994. Min Act: -0.0000

Data Index: 404103 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.3029. Min Act: -0.0000

Data Index: 786948 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.2961. Min Act: -0.0000

Data Index: 881697 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.2731. Min Act: -0.0000

Data Index: 942888 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.2814. Min Act: -0.0000

Data Index: 1133561 (C4 (Web Text))

Max Activating Token Index: 493

Text #12

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.2528. Min Act: -0.0000

Data Index: 725255 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.2537. Min Act: -0.0000

Data Index: 357717 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.2419. Min Act: -0.0000

Data Index: 940885 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.2559. Min Act: -0.0000

Data Index: 774546 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.2440. Min Act: -0.0000

Data Index: 1341261 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.2335. Min Act: -0.0000

Data Index: 422149 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.2656. Min Act: -0.0000

Data Index: 463964 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 0.5952. Min Range: -0.5952

Max Act: 0.2423. Min Act: -0.0000

Data Index: 1218494 (C4 (Web Text))

Max Activating Token Index: 549