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

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

Neuron 3395 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: 2.7489. Min Range: -2.7489

Max Act: 2.5579. Min Act: -0.0000

Data Index: 49223 (C4 (Web Text))

Max Activating Token Index: 341

Text #1

Max Range: 2.7489. Min Range: -2.7489

Max Act: 2.5004. Min Act: -0.0000

Data Index: 672595 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 2.7489. Min Range: -2.7489

Max Act: 2.5801. Min Act: -0.0000

Data Index: 265644 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 2.7489. Min Range: -2.7489

Max Act: 2.4391. Min Act: -0.0000

Data Index: 1013747 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 2.7489. Min Range: -2.7489

Max Act: 2.5724. Min Act: -0.0000

Data Index: 428040 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 2.7489. Min Range: -2.7489

Max Act: 2.4676. Min Act: -0.0000

Data Index: 809568 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 2.7489. Min Range: -2.7489

Max Act: 2.3508. Min Act: -0.0000

Data Index: 973588 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 2.7489. Min Range: -2.7489

Max Act: 2.7489. Min Act: -0.0000

Data Index: 159 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 2.7489. Min Range: -2.7489

Max Act: 2.5606. Min Act: -0.0000

Data Index: 266410 (C4 (Web Text))

Max Activating Token Index: 962

Text #9

Max Range: 2.7489. Min Range: -2.7489

Max Act: 2.3111. Min Act: -0.0000

Data Index: 96614 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 2.7489. Min Range: -2.7489

Max Act: 2.2972. Min Act: -0.0000

Data Index: 967259 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 2.7489. Min Range: -2.7489

Max Act: 2.2931. Min Act: -0.0000

Data Index: 563657 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 2.7489. Min Range: -2.7489

Max Act: 2.2592. Min Act: -0.0000

Data Index: 1274589 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 2.7489. Min Range: -2.7489

Max Act: 2.2508. Min Act: -0.0000

Data Index: 129372 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 2.7489. Min Range: -2.7489

Max Act: 2.3691. Min Act: -0.0000

Data Index: 709943 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 2.7489. Min Range: -2.7489

Max Act: 2.4758. Min Act: -0.0000

Data Index: 640513 (C4 (Web Text))

Max Activating Token Index: 730

Text #16

Max Range: 2.7489. Min Range: -2.7489

Max Act: 2.3239. Min Act: -0.0000

Data Index: 1080411 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 2.7489. Min Range: -2.7489

Max Act: 2.1974. Min Act: -0.0000

Data Index: 353872 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 2.7489. Min Range: -2.7489

Max Act: 2.1797. Min Act: -0.0000

Data Index: 974281 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 2.7489. Min Range: -2.7489

Max Act: 2.5328. Min Act: -0.0000

Data Index: 691321 (C4 (Web Text))

Max Activating Token Index: 984