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

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

Neuron 101 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.6520. Min Act: -0.0000

Data Index: 744684 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.6983. Min Act: -0.0000

Data Index: 787537 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.5991. Min Act: -0.0000

Data Index: 1093776 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.5843. Min Act: -0.0000

Data Index: 501091 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.5648. Min Act: -0.0000

Data Index: 670807 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.5300. Min Act: -0.0000

Data Index: 510258 (C4 (Web Text))

Max Activating Token Index: 895

Text #6

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.5459. Min Act: -0.0000

Data Index: 1277551 (C4 (Web Text))

Max Activating Token Index: 792

Text #7

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.5539. Min Act: -0.0000

Data Index: 21338 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.5193. Min Act: -0.0000

Data Index: 689090 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.5271. Min Act: -0.0000

Data Index: 661831 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.5164. Min Act: -0.0000

Data Index: 921117 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.5144. Min Act: -0.0000

Data Index: 415495 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.5128. Min Act: -0.0000

Data Index: 699459 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.5064. Min Act: -0.0000

Data Index: 177574 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.5031. Min Act: -0.0000

Data Index: 1537169 (Python Code)

Max Activating Token Index: 927

Text #15

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.4738. Min Act: -0.0000

Data Index: 1126806 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.4805. Min Act: -0.0000

Data Index: 804252 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.4665. Min Act: -0.0000

Data Index: 1626543 (Python Code)

Max Activating Token Index: 176

Text #18

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.4622. Min Act: -0.0000

Data Index: 275652 (C4 (Web Text))

Max Activating Token Index: 632

Text #19

Max Range: 0.6983. Min Range: -0.6983

Max Act: 0.4628. Min Act: -0.0000

Data Index: 210414 (C4 (Web Text))

Max Activating Token Index: 59