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

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

Neuron 4489 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: 2.2906. Min Range: -2.2906

Max Act: 2.2906. Min Act: -0.0000

Data Index: 185586 (C4 (Web Text))

Max Activating Token Index: 897

Text #1

Max Range: 2.2906. Min Range: -2.2906

Max Act: 2.0327. Min Act: -0.0000

Data Index: 453495 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 2.2906. Min Range: -2.2906

Max Act: 1.7863. Min Act: -0.0000

Data Index: 133502 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 2.2906. Min Range: -2.2906

Max Act: 1.6118. Min Act: -0.0000

Data Index: 101698 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 2.2906. Min Range: -2.2906

Max Act: 1.5178. Min Act: -0.0000

Data Index: 523047 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 2.2906. Min Range: -2.2906

Max Act: 1.5116. Min Act: -0.0000

Data Index: 525187 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 2.2906. Min Range: -2.2906

Max Act: 1.5771. Min Act: -0.0000

Data Index: 1157887 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 2.2906. Min Range: -2.2906

Max Act: 1.4289. Min Act: -0.0000

Data Index: 574801 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 2.2906. Min Range: -2.2906

Max Act: 1.1969. Min Act: -0.0000

Data Index: 980248 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 2.2906. Min Range: -2.2906

Max Act: 1.4010. Min Act: -0.0000

Data Index: 210584 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 2.2906. Min Range: -2.2906

Max Act: 1.3223. Min Act: -0.0000

Data Index: 633205 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 2.2906. Min Range: -2.2906

Max Act: 1.5761. Min Act: -0.0000

Data Index: 969797 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 2.2906. Min Range: -2.2906

Max Act: 1.5570. Min Act: -0.0000

Data Index: 838342 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 2.2906. Min Range: -2.2906

Max Act: 1.2199. Min Act: -0.0000

Data Index: 113369 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 2.2906. Min Range: -2.2906

Max Act: 1.3701. Min Act: -0.0000

Data Index: 221732 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 2.2906. Min Range: -2.2906

Max Act: 1.1957. Min Act: -0.0000

Data Index: 105628 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 2.2906. Min Range: -2.2906

Max Act: 1.4014. Min Act: -0.0000

Data Index: 377811 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 2.2906. Min Range: -2.2906

Max Act: 1.0214. Min Act: -0.0000

Data Index: 236752 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 2.2906. Min Range: -2.2906

Max Act: 1.3079. Min Act: -0.0000

Data Index: 240783 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 2.2906. Min Range: -2.2906

Max Act: 1.2214. Min Act: -0.0000

Data Index: 1207078 (C4 (Web Text))

Max Activating Token Index: 316