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

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

Neuron 2583 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9893. Min Range: -1.9893

Max Act: 1.9893. Min Act: -0.0000

Data Index: 422124 (C4 (Web Text))

Max Activating Token Index: 270

Text #1

Max Range: 1.9893. Min Range: -1.9893

Max Act: 1.8561. Min Act: -0.0000

Data Index: 475743 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 1.9893. Min Range: -1.9893

Max Act: 1.7161. Min Act: -0.0000

Data Index: 1415240 (Python Code)

Max Activating Token Index: 824

Text #3

Max Range: 1.9893. Min Range: -1.9893

Max Act: 1.8088. Min Act: -0.0000

Data Index: 1487828 (Python Code)

Max Activating Token Index: 40

Text #4

Max Range: 1.9893. Min Range: -1.9893

Max Act: 1.8977. Min Act: -0.0000

Data Index: 102912 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 1.9893. Min Range: -1.9893

Max Act: 1.7595. Min Act: -0.0000

Data Index: 197516 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 1.9893. Min Range: -1.9893

Max Act: 1.8738. Min Act: -0.0000

Data Index: 1593561 (Python Code)

Max Activating Token Index: 237

Text #7

Max Range: 1.9893. Min Range: -1.9893

Max Act: 1.5514. Min Act: -0.0000

Data Index: 1476378 (Python Code)

Max Activating Token Index: 248

Text #8

Max Range: 1.9893. Min Range: -1.9893

Max Act: 1.7717. Min Act: -0.0000

Data Index: 651451 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 1.9893. Min Range: -1.9893

Max Act: 1.7884. Min Act: -0.0000

Data Index: 713248 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 1.9893. Min Range: -1.9893

Max Act: 1.6746. Min Act: -0.0000

Data Index: 647967 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 1.9893. Min Range: -1.9893

Max Act: 1.6656. Min Act: -0.0000

Data Index: 819070 (C4 (Web Text))

Max Activating Token Index: 892

Text #12

Max Range: 1.9893. Min Range: -1.9893

Max Act: 1.5798. Min Act: -0.0000

Data Index: 266203 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 1.9893. Min Range: -1.9893

Max Act: 1.6497. Min Act: -0.0000

Data Index: 141617 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 1.9893. Min Range: -1.9893

Max Act: 1.6353. Min Act: -0.0000

Data Index: 1301785 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 1.9893. Min Range: -1.9893

Max Act: 1.7362. Min Act: -0.0000

Data Index: 1029461 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 1.9893. Min Range: -1.9893

Max Act: 1.5556. Min Act: -0.0000

Data Index: 1509992 (Python Code)

Max Activating Token Index: 217

Text #17

Max Range: 1.9893. Min Range: -1.9893

Max Act: 1.5597. Min Act: -0.0000

Data Index: 263304 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 1.9893. Min Range: -1.9893

Max Act: 1.5408. Min Act: -0.0000

Data Index: 336257 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 1.9893. Min Range: -1.9893

Max Act: 1.5353. Min Act: -0.0000

Data Index: 235315 (C4 (Web Text))

Max Activating Token Index: 136