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

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

Neuron 4654 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7505. Min Range: -2.7505

Max Act: 2.6327. Min Act: -0.0000

Data Index: 915469 (C4 (Web Text))

Max Activating Token Index: 400

Text #1

Max Range: 2.7505. Min Range: -2.7505

Max Act: 2.7505. Min Act: -0.0000

Data Index: 836041 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 2.7505. Min Range: -2.7505

Max Act: 2.6542. Min Act: -0.0000

Data Index: 668496 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 2.7505. Min Range: -2.7505

Max Act: 2.4909. Min Act: -0.0000

Data Index: 795156 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 2.7505. Min Range: -2.7505

Max Act: 2.4422. Min Act: -0.0000

Data Index: 1289212 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 2.7505. Min Range: -2.7505

Max Act: 2.5251. Min Act: -0.0000

Data Index: 283009 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 2.7505. Min Range: -2.7505

Max Act: 2.4061. Min Act: -0.0000

Data Index: 819165 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 2.7505. Min Range: -2.7505

Max Act: 2.1372. Min Act: -0.0000

Data Index: 1303571 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 2.7505. Min Range: -2.7505

Max Act: 2.2664. Min Act: -0.0000

Data Index: 866438 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 2.7505. Min Range: -2.7505

Max Act: 2.2739. Min Act: -0.0000

Data Index: 985013 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 2.7505. Min Range: -2.7505

Max Act: 2.2074. Min Act: -0.0000

Data Index: 1165010 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 2.7505. Min Range: -2.7505

Max Act: 2.3470. Min Act: -0.0000

Data Index: 703745 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 2.7505. Min Range: -2.7505

Max Act: 2.2263. Min Act: -0.0000

Data Index: 1172022 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 2.7505. Min Range: -2.7505

Max Act: 2.0128. Min Act: -0.0000

Data Index: 1087995 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 2.7505. Min Range: -2.7505

Max Act: 2.3240. Min Act: -0.0000

Data Index: 387318 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 2.7505. Min Range: -2.7505

Max Act: 2.3096. Min Act: -0.0000

Data Index: 1338361 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 2.7505. Min Range: -2.7505

Max Act: 2.3057. Min Act: -0.0000

Data Index: 582680 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 2.7505. Min Range: -2.7505

Max Act: 2.1897. Min Act: -0.0000

Data Index: 641706 (C4 (Web Text))

Max Activating Token Index: 615

Text #18

Max Range: 2.7505. Min Range: -2.7505

Max Act: 2.2963. Min Act: -0.0000

Data Index: 940841 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 2.7505. Min Range: -2.7505

Max Act: 2.1844. Min Act: -0.0000

Data Index: 800237 (C4 (Web Text))

Max Activating Token Index: 38