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

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

Neuron 1638 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.4354. Min Act: -0.0000

Data Index: 1257300 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.4179. Min Act: -0.0000

Data Index: 1042199 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.4093. Min Act: -0.0000

Data Index: 847567 (C4 (Web Text))

Max Activating Token Index: 511

Text #3

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3799. Min Act: -0.0000

Data Index: 395012 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3719. Min Act: -0.0000

Data Index: 712433 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3544. Min Act: -0.0000

Data Index: 1170095 (C4 (Web Text))

Max Activating Token Index: 286

Text #6

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3465. Min Act: -0.0000

Data Index: 275815 (C4 (Web Text))

Max Activating Token Index: 187

Text #7

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3593. Min Act: 0.0000

Data Index: 512111 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3531. Min Act: -0.0000

Data Index: 1087222 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3448. Min Act: -0.0000

Data Index: 769897 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3122. Min Act: -0.0000

Data Index: 1421163 (Python Code)

Max Activating Token Index: 320

Text #11

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3288. Min Act: -0.0000

Data Index: 602544 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2995. Min Act: -0.0000

Data Index: 1611193 (Python Code)

Max Activating Token Index: 157

Text #13

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3046. Min Act: -0.0000

Data Index: 384210 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.3130. Min Act: -0.0000

Data Index: 1469510 (Python Code)

Max Activating Token Index: 987

Text #15

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2869. Min Act: 0.0000

Data Index: 237621 (C4 (Web Text))

Max Activating Token Index: 897

Text #16

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2960. Min Act: -0.0000

Data Index: 598375 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2703. Min Act: -0.0000

Data Index: 451629 (C4 (Web Text))

Max Activating Token Index: 726

Text #18

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2887. Min Act: 0.0000

Data Index: 263017 (C4 (Web Text))

Max Activating Token Index: 331

Text #19

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2793. Min Act: -0.0000

Data Index: 135159 (C4 (Web Text))

Max Activating Token Index: 147