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

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

Neuron 4823 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3950. Min Range: -1.3950

Max Act: 1.3950. Min Act: -0.0000

Data Index: 762713 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 1.3950. Min Range: -1.3950

Max Act: 1.3087. Min Act: -0.0000

Data Index: 1265074 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 1.3950. Min Range: -1.3950

Max Act: 1.2134. Min Act: -0.0000

Data Index: 395370 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 1.3950. Min Range: -1.3950

Max Act: 1.2689. Min Act: -0.0000

Data Index: 1245763 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 1.3950. Min Range: -1.3950

Max Act: 1.2638. Min Act: -0.0000

Data Index: 833336 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 1.3950. Min Range: -1.3950

Max Act: 1.1768. Min Act: -0.0000

Data Index: 240564 (C4 (Web Text))

Max Activating Token Index: 137

Text #6

Max Range: 1.3950. Min Range: -1.3950

Max Act: 1.1152. Min Act: -0.0000

Data Index: 721610 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 1.3950. Min Range: -1.3950

Max Act: 1.2030. Min Act: -0.0000

Data Index: 797782 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 1.3950. Min Range: -1.3950

Max Act: 1.1102. Min Act: -0.0000

Data Index: 779089 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 1.3950. Min Range: -1.3950

Max Act: 1.1047. Min Act: -0.0000

Data Index: 394046 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 1.3950. Min Range: -1.3950

Max Act: 1.0136. Min Act: -0.0000

Data Index: 1329169 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 1.3950. Min Range: -1.3950

Max Act: 1.0767. Min Act: -0.0000

Data Index: 1218078 (C4 (Web Text))

Max Activating Token Index: 525

Text #12

Max Range: 1.3950. Min Range: -1.3950

Max Act: 1.0768. Min Act: -0.0000

Data Index: 592260 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 1.3950. Min Range: -1.3950

Max Act: 1.0374. Min Act: -0.0000

Data Index: 511521 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 1.3950. Min Range: -1.3950

Max Act: 1.0460. Min Act: -0.0000

Data Index: 1134984 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 1.3950. Min Range: -1.3950

Max Act: 1.0341. Min Act: -0.0000

Data Index: 1236873 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 1.3950. Min Range: -1.3950

Max Act: 1.0111. Min Act: -0.0000

Data Index: 59210 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 1.3950. Min Range: -1.3950

Max Act: 0.9694. Min Act: -0.0000

Data Index: 500039 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 1.3950. Min Range: -1.3950

Max Act: 1.0142. Min Act: -0.0000

Data Index: 298128 (C4 (Web Text))

Max Activating Token Index: 654

Text #19

Max Range: 1.3950. Min Range: -1.3950

Max Act: 1.0103. Min Act: -0.0000

Data Index: 238136 (C4 (Web Text))

Max Activating Token Index: 181