Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2168 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.6815. Min Act: -0.0003

Data Index: 722413 (C4 (Web Text))

Max Activating Token Index: 202

Text #1

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.6168. Min Act: -0.0003

Data Index: 467045 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.6138. Min Act: -0.0003

Data Index: 467153 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.6069. Min Act: -0.0003

Data Index: 64877 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5574. Min Act: -0.0003

Data Index: 777502 (C4 (Web Text))

Max Activating Token Index: 652

Text #5

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5927. Min Act: -0.0003

Data Index: 1209583 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5492. Min Act: -0.0003

Data Index: 1147952 (C4 (Web Text))

Max Activating Token Index: 340

Text #7

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5639. Min Act: -0.0003

Data Index: 523968 (C4 (Web Text))

Max Activating Token Index: 720

Text #8

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5622. Min Act: -0.0003

Data Index: 1313384 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5578. Min Act: -0.0003

Data Index: 1322747 (C4 (Web Text))

Max Activating Token Index: 795

Text #10

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5529. Min Act: -0.0003

Data Index: 989861 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5692. Min Act: -0.0003

Data Index: 1253154 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5345. Min Act: -0.0002

Data Index: 203196 (C4 (Web Text))

Max Activating Token Index: 433

Text #13

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5331. Min Act: -0.0003

Data Index: 759269 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5146. Min Act: -0.0003

Data Index: 231440 (C4 (Web Text))

Max Activating Token Index: 92

Text #15

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5500. Min Act: -0.0003

Data Index: 1305132 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5311. Min Act: -0.0003

Data Index: 436412 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5241. Min Act: -0.0003

Data Index: 866025 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5216. Min Act: -0.0002

Data Index: 1352185 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 0.6815. Min Range: -0.6815

Max Act: 0.5152. Min Act: -0.0003

Data Index: 373503 (C4 (Web Text))

Max Activating Token Index: 579