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

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

Neuron 4638 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2793. Min Range: -1.2793

Max Act: 1.2793. Min Act: -0.0001

Data Index: 794515 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 1.2793. Min Range: -1.2793

Max Act: 1.0930. Min Act: -0.0001

Data Index: 547161 (C4 (Web Text))

Max Activating Token Index: 432

Text #2

Max Range: 1.2793. Min Range: -1.2793

Max Act: 1.1339. Min Act: -0.0001

Data Index: 228914 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 1.2793. Min Range: -1.2793

Max Act: 1.0505. Min Act: -0.0001

Data Index: 786887 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.9284. Min Act: -0.0000

Data Index: 1545312 (Python Code)

Max Activating Token Index: 962

Text #5

Max Range: 1.2793. Min Range: -1.2793

Max Act: 1.0172. Min Act: -0.0001

Data Index: 1227439 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.9838. Min Act: -0.0001

Data Index: 843132 (C4 (Web Text))

Max Activating Token Index: 458

Text #7

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.9077. Min Act: -0.0001

Data Index: 802336 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.9294. Min Act: -0.0001

Data Index: 1286929 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.8933. Min Act: -0.0001

Data Index: 1163087 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.8850. Min Act: -0.0001

Data Index: 1237552 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.9746. Min Act: -0.0001

Data Index: 1231870 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.8867. Min Act: -0.0001

Data Index: 1272369 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.8359. Min Act: -0.0001

Data Index: 306941 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.8595. Min Act: -0.0001

Data Index: 44161 (C4 (Web Text))

Max Activating Token Index: 559

Text #15

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.8714. Min Act: -0.0001

Data Index: 772457 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.8218. Min Act: -0.0001

Data Index: 599576 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.7878. Min Act: -0.0001

Data Index: 235441 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.7997. Min Act: -0.0001

Data Index: 1148715 (C4 (Web Text))

Max Activating Token Index: 799

Text #19

Max Range: 1.2793. Min Range: -1.2793

Max Act: 0.8001. Min Act: -0.0001

Data Index: 1019292 (C4 (Web Text))

Max Activating Token Index: 286