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

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

Neuron 2149 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.8784. Min Act: -0.0000

Data Index: 963919 (C4 (Web Text))

Max Activating Token Index: 523

Text #1

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7210. Min Act: 0.0000

Data Index: 1015681 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.7204. Min Act: -0.0000

Data Index: 1259616 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.6224. Min Act: -0.0000

Data Index: 264666 (C4 (Web Text))

Max Activating Token Index: 650

Text #4

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.6093. Min Act: -0.0000

Data Index: 159027 (C4 (Web Text))

Max Activating Token Index: 56

Text #5

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.5853. Min Act: -0.0000

Data Index: 18433 (C4 (Web Text))

Max Activating Token Index: 815

Text #6

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.5755. Min Act: 0.0000

Data Index: 240305 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.5530. Min Act: -0.0000

Data Index: 1004718 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.5645. Min Act: -0.0000

Data Index: 70400 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.5588. Min Act: -0.0000

Data Index: 1345674 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.5763. Min Act: -0.0000

Data Index: 579078 (C4 (Web Text))

Max Activating Token Index: 69

Text #11

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.5788. Min Act: 0.0000

Data Index: 1176143 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.5605. Min Act: -0.0000

Data Index: 538651 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.5636. Min Act: -0.0000

Data Index: 1041526 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.5423. Min Act: 0.0000

Data Index: 994842 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.5288. Min Act: -0.0000

Data Index: 1348857 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.5165. Min Act: -0.0000

Data Index: 1249635 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.5283. Min Act: -0.0000

Data Index: 933482 (C4 (Web Text))

Max Activating Token Index: 525

Text #18

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.5241. Min Act: -0.0000

Data Index: 1335889 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 0.8784. Min Range: -0.8784

Max Act: 0.5205. Min Act: -0.0000

Data Index: 61102 (C4 (Web Text))

Max Activating Token Index: 751