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

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

Neuron 5064 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: 1.5443. Min Range: -1.5443

Max Act: 1.5443. Min Act: -0.0000

Data Index: 385323 (C4 (Web Text))

Max Activating Token Index: 482

Text #1

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.2770. Min Act: -0.0000

Data Index: 1321493 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.2162. Min Act: -0.0000

Data Index: 784808 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.2127. Min Act: -0.0000

Data Index: 491829 (C4 (Web Text))

Max Activating Token Index: 231

Text #4

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.2752. Min Act: -0.0000

Data Index: 812497 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.1064. Min Act: -0.0000

Data Index: 402968 (C4 (Web Text))

Max Activating Token Index: 482

Text #6

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.0739. Min Act: -0.0000

Data Index: 410575 (C4 (Web Text))

Max Activating Token Index: 628

Text #7

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.0568. Min Act: -0.0000

Data Index: 365526 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.0471. Min Act: -0.0000

Data Index: 145086 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 1.5443. Min Range: -1.5443

Max Act: 1.0516. Min Act: -0.0000

Data Index: 299359 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 1.5443. Min Range: -1.5443

Max Act: 0.9835. Min Act: -0.0000

Data Index: 1078780 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 1.5443. Min Range: -1.5443

Max Act: 0.9110. Min Act: -0.0000

Data Index: 657414 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 1.5443. Min Range: -1.5443

Max Act: 0.8794. Min Act: -0.0000

Data Index: 555172 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 1.5443. Min Range: -1.5443

Max Act: 0.8472. Min Act: -0.0000

Data Index: 175777 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 1.5443. Min Range: -1.5443

Max Act: 0.9283. Min Act: -0.0000

Data Index: 825300 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 1.5443. Min Range: -1.5443

Max Act: 0.8464. Min Act: -0.0000

Data Index: 175431 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 1.5443. Min Range: -1.5443

Max Act: 0.7956. Min Act: -0.0000

Data Index: 547396 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 1.5443. Min Range: -1.5443

Max Act: 0.7877. Min Act: -0.0000

Data Index: 1053140 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 1.5443. Min Range: -1.5443

Max Act: 0.7376. Min Act: -0.0000

Data Index: 743343 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 1.5443. Min Range: -1.5443

Max Act: 0.7813. Min Act: -0.0000

Data Index: 884225 (C4 (Web Text))

Max Activating Token Index: 75