Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3455 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.8613. Min Act: -0.0002

Data Index: 130598 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.8249. Min Act: -0.0001

Data Index: 1046071 (C4 (Web Text))

Max Activating Token Index: 943

Text #2

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7715. Min Act: -0.0002

Data Index: 1045368 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7598. Min Act: -0.0001

Data Index: 178384 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7572. Min Act: -0.0002

Data Index: 220921 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7683. Min Act: -0.0001

Data Index: 128773 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7982. Min Act: -0.0001

Data Index: 1142754 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7780. Min Act: -0.0002

Data Index: 1153209 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7499. Min Act: -0.0002

Data Index: 549638 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7565. Min Act: -0.0002

Data Index: 1180840 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7215. Min Act: -0.0001

Data Index: 423188 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7572. Min Act: -0.0002

Data Index: 570267 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7008. Min Act: -0.0001

Data Index: 902670 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7903. Min Act: -0.0001

Data Index: 1027841 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7138. Min Act: -0.0001

Data Index: 941228 (C4 (Web Text))

Max Activating Token Index: 827

Text #15

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7514. Min Act: -0.0001

Data Index: 742789 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7248. Min Act: -0.0001

Data Index: 1004880 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7353. Min Act: -0.0002

Data Index: 1144888 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.7106. Min Act: -0.0002

Data Index: 1160701 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 0.8613. Min Range: -0.8613

Max Act: 0.6485. Min Act: -0.0001

Data Index: 1242756 (C4 (Web Text))

Max Activating Token Index: 80