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

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

Neuron 2341 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.7858. Min Act: -0.0002

Data Index: 250833 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.7486. Min Act: -0.0002

Data Index: 882465 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.7567. Min Act: -0.0002

Data Index: 312648 (C4 (Web Text))

Max Activating Token Index: 374

Text #3

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.7351. Min Act: -0.0002

Data Index: 1111147 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.7148. Min Act: -0.0002

Data Index: 218947 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.7094. Min Act: -0.0002

Data Index: 547776 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.7395. Min Act: -0.0002

Data Index: 684885 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.7196. Min Act: -0.0002

Data Index: 56771 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.6927. Min Act: -0.0002

Data Index: 1209078 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.7003. Min Act: -0.0002

Data Index: 425618 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.6987. Min Act: -0.0002

Data Index: 713436 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.7034. Min Act: -0.0003

Data Index: 923719 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.6948. Min Act: -0.0002

Data Index: 427740 (C4 (Web Text))

Max Activating Token Index: 686

Text #13

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.6933. Min Act: -0.0002

Data Index: 775178 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.6833. Min Act: -0.0002

Data Index: 1058916 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.6922. Min Act: -0.0002

Data Index: 1200381 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.6903. Min Act: -0.0002

Data Index: 1206088 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.6675. Min Act: -0.0002

Data Index: 426527 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.6719. Min Act: -0.0002

Data Index: 62247 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 0.7858. Min Range: -0.7858

Max Act: 0.6800. Min Act: -0.0002

Data Index: 1056295 (C4 (Web Text))

Max Activating Token Index: 604