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

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

Neuron 5003 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: 3.0755. Min Range: -3.0755

Max Act: 3.0755. Min Act: -0.0000

Data Index: 739195 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 3.0755. Min Range: -3.0755

Max Act: 2.9726. Min Act: -0.0000

Data Index: 517313 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 3.0755. Min Range: -3.0755

Max Act: 2.7705. Min Act: -0.0000

Data Index: 375015 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 3.0755. Min Range: -3.0755

Max Act: 2.6634. Min Act: -0.0000

Data Index: 492701 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 3.0755. Min Range: -3.0755

Max Act: 2.5444. Min Act: -0.0000

Data Index: 340461 (C4 (Web Text))

Max Activating Token Index: 88

Text #5

Max Range: 3.0755. Min Range: -3.0755

Max Act: 2.5128. Min Act: -0.0000

Data Index: 1108093 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 3.0755. Min Range: -3.0755

Max Act: 2.3578. Min Act: -0.0000

Data Index: 551697 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 3.0755. Min Range: -3.0755

Max Act: 2.4584. Min Act: -0.0000

Data Index: 345977 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 3.0755. Min Range: -3.0755

Max Act: 2.5791. Min Act: -0.0000

Data Index: 1271473 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 3.0755. Min Range: -3.0755

Max Act: 2.5610. Min Act: -0.0000

Data Index: 324330 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 3.0755. Min Range: -3.0755

Max Act: 2.3009. Min Act: -0.0000

Data Index: 441034 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 3.0755. Min Range: -3.0755

Max Act: 2.4349. Min Act: -0.0000

Data Index: 559311 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 3.0755. Min Range: -3.0755

Max Act: 2.2833. Min Act: -0.0000

Data Index: 679546 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 3.0755. Min Range: -3.0755

Max Act: 2.2641. Min Act: -0.0000

Data Index: 519984 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 3.0755. Min Range: -3.0755

Max Act: 2.2158. Min Act: -0.0000

Data Index: 1076345 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 3.0755. Min Range: -3.0755

Max Act: 2.3435. Min Act: -0.0000

Data Index: 747255 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 3.0755. Min Range: -3.0755

Max Act: 2.2083. Min Act: -0.0000

Data Index: 222489 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 3.0755. Min Range: -3.0755

Max Act: 2.4489. Min Act: -0.0000

Data Index: 207678 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 3.0755. Min Range: -3.0755

Max Act: 2.1951. Min Act: -0.0000

Data Index: 1193774 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 3.0755. Min Range: -3.0755

Max Act: 2.3023. Min Act: -0.0000

Data Index: 828490 (C4 (Web Text))

Max Activating Token Index: 83