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

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

Neuron 3837 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.2137. Min Range: -6.2137

Max Act: 6.2137. Min Act: -0.0000

Data Index: 1000595 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 6.2137. Min Range: -6.2137

Max Act: 6.0038. Min Act: -0.0001

Data Index: 583840 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 6.2137. Min Range: -6.2137

Max Act: 5.4852. Min Act: -0.0001

Data Index: 91641 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 6.2137. Min Range: -6.2137

Max Act: 4.6436. Min Act: -0.0000

Data Index: 1004801 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 6.2137. Min Range: -6.2137

Max Act: 4.9613. Min Act: -0.0001

Data Index: 770761 (C4 (Web Text))

Max Activating Token Index: 440

Text #5

Max Range: 6.2137. Min Range: -6.2137

Max Act: 5.4668. Min Act: -0.0001

Data Index: 337212 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 6.2137. Min Range: -6.2137

Max Act: 4.7634. Min Act: -0.0001

Data Index: 413140 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 6.2137. Min Range: -6.2137

Max Act: 4.9967. Min Act: -0.0001

Data Index: 1169617 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 6.2137. Min Range: -6.2137

Max Act: 5.3302. Min Act: -0.0000

Data Index: 632157 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 6.2137. Min Range: -6.2137

Max Act: 4.9456. Min Act: -0.0001

Data Index: 866133 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 6.2137. Min Range: -6.2137

Max Act: 5.0070. Min Act: -0.0000

Data Index: 561852 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 6.2137. Min Range: -6.2137

Max Act: 4.9329. Min Act: -0.0000

Data Index: 466062 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 6.2137. Min Range: -6.2137

Max Act: 4.6638. Min Act: -0.0001

Data Index: 855482 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 6.2137. Min Range: -6.2137

Max Act: 4.5382. Min Act: -0.0001

Data Index: 240467 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 6.2137. Min Range: -6.2137

Max Act: 4.6796. Min Act: -0.0001

Data Index: 482362 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 6.2137. Min Range: -6.2137

Max Act: 3.6979. Min Act: -0.0000

Data Index: 428983 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 6.2137. Min Range: -6.2137

Max Act: 4.2719. Min Act: -0.0000

Data Index: 105725 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 6.2137. Min Range: -6.2137

Max Act: 4.4519. Min Act: -0.0001

Data Index: 649967 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 6.2137. Min Range: -6.2137

Max Act: 4.5963. Min Act: -0.0000

Data Index: 805535 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 6.2137. Min Range: -6.2137

Max Act: 4.5566. Min Act: -0.0001

Data Index: 812289 (C4 (Web Text))

Max Activating Token Index: 1016