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

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

Neuron 1209 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.8384. Min Act: -0.0000

Data Index: 963567 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.7703. Min Act: -0.0000

Data Index: 476103 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.7644. Min Act: -0.0000

Data Index: 776017 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.7515. Min Act: -0.0000

Data Index: 818287 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.7700. Min Act: -0.0000

Data Index: 171000 (C4 (Web Text))

Max Activating Token Index: 506

Text #5

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.7887. Min Act: -0.0000

Data Index: 161421 (C4 (Web Text))

Max Activating Token Index: 278

Text #6

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.7250. Min Act: -0.0000

Data Index: 723656 (C4 (Web Text))

Max Activating Token Index: 138

Text #7

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.7864. Min Act: -0.0000

Data Index: 1093417 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.7348. Min Act: -0.0000

Data Index: 580780 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.8032. Min Act: -0.0000

Data Index: 658289 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.7791. Min Act: -0.0000

Data Index: 412928 (C4 (Web Text))

Max Activating Token Index: 519

Text #11

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.7622. Min Act: -0.0000

Data Index: 944403 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.7576. Min Act: -0.0000

Data Index: 1224431 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.7597. Min Act: -0.0000

Data Index: 735023 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.7580. Min Act: -0.0000

Data Index: 291359 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.7257. Min Act: -0.0000

Data Index: 810501 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.8240. Min Act: -0.0000

Data Index: 1100453 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.7416. Min Act: -0.0000

Data Index: 897625 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.7146. Min Act: -0.0000

Data Index: 87266 (C4 (Web Text))

Max Activating Token Index: 524

Text #19

Max Range: 0.8384. Min Range: -0.8384

Max Act: 0.7341. Min Act: -0.0000

Data Index: 683115 (C4 (Web Text))

Max Activating Token Index: 433