Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2634 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.5323. Min Act: -0.0001

Data Index: 121411 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.2437. Min Act: -0.0001

Data Index: 753935 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.2214. Min Act: -0.0001

Data Index: 630796 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.1922. Min Act: -0.0001

Data Index: 969722 (C4 (Web Text))

Max Activating Token Index: 538

Text #4

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.1211. Min Act: -0.0001

Data Index: 493028 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.1383. Min Act: -0.0001

Data Index: 454273 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.1118. Min Act: -0.0001

Data Index: 983928 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.0406. Min Act: -0.0001

Data Index: 569533 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.0314. Min Act: -0.0001

Data Index: 2758 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.0897. Min Act: -0.0001

Data Index: 546640 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.0473. Min Act: -0.0001

Data Index: 418128 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.0324. Min Act: -0.0001

Data Index: 1058104 (C4 (Web Text))

Max Activating Token Index: 620

Text #12

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.0010. Min Act: -0.0001

Data Index: 366953 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.0018. Min Act: -0.0001

Data Index: 341274 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.0536. Min Act: -0.0001

Data Index: 381311 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 1.5323. Min Range: -1.5323

Max Act: 0.9644. Min Act: -0.0001

Data Index: 458077 (C4 (Web Text))

Max Activating Token Index: 640

Text #16

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.0804. Min Act: -0.0001

Data Index: 745668 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 1.5323. Min Range: -1.5323

Max Act: 1.0051. Min Act: -0.0001

Data Index: 1216581 (C4 (Web Text))

Max Activating Token Index: 500

Text #18

Max Range: 1.5323. Min Range: -1.5323

Max Act: 0.9816. Min Act: -0.0001

Data Index: 681681 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 1.5323. Min Range: -1.5323

Max Act: 0.9954. Min Act: -0.0001

Data Index: 899256 (C4 (Web Text))

Max Activating Token Index: 761