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

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

Neuron 4187 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.7397. Min Act: -0.0000

Data Index: 488964 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.6031. Min Act: -0.0000

Data Index: 359453 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.5674. Min Act: -0.0000

Data Index: 367607 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.5926. Min Act: -0.0000

Data Index: 684922 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.4941. Min Act: -0.0000

Data Index: 425317 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.4846. Min Act: -0.0000

Data Index: 856988 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.4789. Min Act: -0.0000

Data Index: 826684 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.4770. Min Act: -0.0000

Data Index: 888431 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.4175. Min Act: -0.0000

Data Index: 1040622 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.4261. Min Act: -0.0000

Data Index: 608678 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.4030. Min Act: -0.0000

Data Index: 1089889 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.4005. Min Act: -0.0000

Data Index: 410277 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.4105. Min Act: -0.0000

Data Index: 995269 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.3730. Min Act: -0.0000

Data Index: 1321432 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.3981. Min Act: -0.0000

Data Index: 116547 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.3922. Min Act: -0.0000

Data Index: 293065 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.4322. Min Act: -0.0000

Data Index: 821886 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.3959. Min Act: -0.0000

Data Index: 1263464 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.3842. Min Act: -0.0000

Data Index: 1259437 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 0.7397. Min Range: -0.7397

Max Act: 0.3654. Min Act: -0.0000

Data Index: 959411 (C4 (Web Text))

Max Activating Token Index: 978