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

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

Neuron 3344 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.4706. Min Act: -0.0000

Data Index: 1154356 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.4530. Min Act: -0.0000

Data Index: 673194 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.4201. Min Act: -0.0000

Data Index: 689788 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3645. Min Act: -0.0000

Data Index: 468317 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3626. Min Act: -0.0000

Data Index: 779254 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3637. Min Act: -0.0000

Data Index: 597925 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3617. Min Act: -0.0000

Data Index: 191286 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3478. Min Act: -0.0000

Data Index: 182439 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3475. Min Act: -0.0000

Data Index: 514186 (C4 (Web Text))

Max Activating Token Index: 299

Text #9

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3344. Min Act: -0.0000

Data Index: 142921 (C4 (Web Text))

Max Activating Token Index: 427

Text #10

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3203. Min Act: -0.0000

Data Index: 664641 (C4 (Web Text))

Max Activating Token Index: 295

Text #11

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3323. Min Act: -0.0000

Data Index: 866833 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3343. Min Act: -0.0000

Data Index: 997445 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3164. Min Act: -0.0000

Data Index: 68274 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3375. Min Act: -0.0000

Data Index: 322560 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3402. Min Act: -0.0000

Data Index: 226596 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3270. Min Act: -0.0000

Data Index: 322362 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3262. Min Act: -0.0000

Data Index: 148299 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3238. Min Act: -0.0000

Data Index: 1232492 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 0.4706. Min Range: -0.4706

Max Act: 0.3394. Min Act: -0.0000

Data Index: 335539 (C4 (Web Text))

Max Activating Token Index: 798