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

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

Neuron 309 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4303. Min Range: -1.4303

Max Act: 1.4303. Min Act: -0.0000

Data Index: 1272109 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 1.4303. Min Range: -1.4303

Max Act: 1.3964. Min Act: -0.0000

Data Index: 646561 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 1.4303. Min Range: -1.4303

Max Act: 1.1723. Min Act: -0.0000

Data Index: 936373 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 1.4303. Min Range: -1.4303

Max Act: 1.0898. Min Act: -0.0000

Data Index: 625740 (C4 (Web Text))

Max Activating Token Index: 222

Text #4

Max Range: 1.4303. Min Range: -1.4303

Max Act: 1.1214. Min Act: -0.0000

Data Index: 238136 (C4 (Web Text))

Max Activating Token Index: 844

Text #5

Max Range: 1.4303. Min Range: -1.4303

Max Act: 1.0658. Min Act: -0.0000

Data Index: 1260338 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 1.4303. Min Range: -1.4303

Max Act: 1.0230. Min Act: -0.0000

Data Index: 512077 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 1.4303. Min Range: -1.4303

Max Act: 1.0616. Min Act: -0.0000

Data Index: 423260 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 1.4303. Min Range: -1.4303

Max Act: 0.9955. Min Act: -0.0000

Data Index: 1102770 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 1.4303. Min Range: -1.4303

Max Act: 0.9832. Min Act: -0.0000

Data Index: 274145 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 1.4303. Min Range: -1.4303

Max Act: 1.0407. Min Act: -0.0000

Data Index: 1188807 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 1.4303. Min Range: -1.4303

Max Act: 1.0033. Min Act: -0.0000

Data Index: 673663 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 1.4303. Min Range: -1.4303

Max Act: 1.0304. Min Act: -0.0000

Data Index: 608358 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 1.4303. Min Range: -1.4303

Max Act: 1.0693. Min Act: -0.0000

Data Index: 17436 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 1.4303. Min Range: -1.4303

Max Act: 1.0513. Min Act: -0.0000

Data Index: 404355 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 1.4303. Min Range: -1.4303

Max Act: 0.9843. Min Act: -0.0000

Data Index: 652930 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 1.4303. Min Range: -1.4303

Max Act: 0.9855. Min Act: -0.0000

Data Index: 1159214 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 1.4303. Min Range: -1.4303

Max Act: 0.9754. Min Act: -0.0000

Data Index: 1263529 (C4 (Web Text))

Max Activating Token Index: 367

Text #18

Max Range: 1.4303. Min Range: -1.4303

Max Act: 1.0036. Min Act: -0.0000

Data Index: 726449 (C4 (Web Text))

Max Activating Token Index: 916

Text #19

Max Range: 1.4303. Min Range: -1.4303

Max Act: 0.9687. Min Act: -0.0000

Data Index: 950301 (C4 (Web Text))

Max Activating Token Index: 413