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

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

Neuron 3222 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.6160. Min Act: -0.0001

Data Index: 97225 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.5307. Min Act: -0.0001

Data Index: 713564 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.5651. Min Act: -0.0001

Data Index: 590801 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.5387. Min Act: -0.0001

Data Index: 1025255 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.5276. Min Act: -0.0001

Data Index: 224179 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.5706. Min Act: -0.0001

Data Index: 652030 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.5623. Min Act: -0.0001

Data Index: 975634 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.4606. Min Act: -0.0001

Data Index: 526490 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.5020. Min Act: -0.0001

Data Index: 241273 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.4706. Min Act: -0.0001

Data Index: 454674 (C4 (Web Text))

Max Activating Token Index: 798

Text #10

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.5055. Min Act: -0.0001

Data Index: 469273 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.4961. Min Act: -0.0001

Data Index: 188524 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.4759. Min Act: -0.0001

Data Index: 894517 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.4803. Min Act: -0.0001

Data Index: 137510 (C4 (Web Text))

Max Activating Token Index: 646

Text #14

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.5210. Min Act: -0.0001

Data Index: 353813 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.4719. Min Act: -0.0001

Data Index: 385165 (C4 (Web Text))

Max Activating Token Index: 113

Text #16

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.4836. Min Act: -0.0001

Data Index: 302165 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.4781. Min Act: -0.0001

Data Index: 1284466 (C4 (Web Text))

Max Activating Token Index: 431

Text #18

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.5048. Min Act: -0.0001

Data Index: 747054 (C4 (Web Text))

Max Activating Token Index: 899

Text #19

Max Range: 0.6160. Min Range: -0.6160

Max Act: 0.5157. Min Act: -0.0001

Data Index: 894666 (C4 (Web Text))

Max Activating Token Index: 240