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

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

Neuron 5898 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4408. Min Range: -0.4408

Max Act: 0.4408. Min Act: -0.0000

Data Index: 71776 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 0.4408. Min Range: -0.4408

Max Act: 0.4097. Min Act: -0.0000

Data Index: 465588 (C4 (Web Text))

Max Activating Token Index: 609

Text #2

Max Range: 0.4408. Min Range: -0.4408

Max Act: 0.3956. Min Act: -0.0000

Data Index: 991256 (C4 (Web Text))

Max Activating Token Index: 378

Text #3

Max Range: 0.4408. Min Range: -0.4408

Max Act: 0.4092. Min Act: -0.0000

Data Index: 109399 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 0.4408. Min Range: -0.4408

Max Act: 0.3761. Min Act: -0.0000

Data Index: 637575 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 0.4408. Min Range: -0.4408

Max Act: 0.3772. Min Act: -0.0000

Data Index: 485284 (C4 (Web Text))

Max Activating Token Index: 558

Text #6

Max Range: 0.4408. Min Range: -0.4408

Max Act: 0.3982. Min Act: -0.0000

Data Index: 467996 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 0.4408. Min Range: -0.4408

Max Act: 0.3809. Min Act: -0.0000

Data Index: 902587 (C4 (Web Text))

Max Activating Token Index: 343

Text #8

Max Range: 0.4408. Min Range: -0.4408

Max Act: 0.3784. Min Act: -0.0000

Data Index: 385386 (C4 (Web Text))

Max Activating Token Index: 760

Text #9

Max Range: 0.4408. Min Range: -0.4408

Max Act: 0.3562. Min Act: -0.0000

Data Index: 265406 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 0.4408. Min Range: -0.4408

Max Act: 0.3425. Min Act: -0.0000

Data Index: 362389 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 0.4408. Min Range: -0.4408

Max Act: 0.2868. Min Act: -0.0000

Data Index: 84434 (C4 (Web Text))

Max Activating Token Index: 219

Text #12

Max Range: 0.4408. Min Range: -0.4408

Max Act: 0.2788. Min Act: -0.0000

Data Index: 998603 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 0.4408. Min Range: -0.4408

Max Act: 0.2775. Min Act: -0.0000

Data Index: 726684 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 0.4408. Min Range: -0.4408

Max Act: 0.2773. Min Act: -0.0000

Data Index: 1234075 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 0.4408. Min Range: -0.4408

Max Act: 0.2631. Min Act: -0.0000

Data Index: 1309554 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 0.4408. Min Range: -0.4408

Max Act: 0.2449. Min Act: -0.0000

Data Index: 973138 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 0.4408. Min Range: -0.4408

Max Act: 0.2255. Min Act: -0.0000

Data Index: 162633 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 0.4408. Min Range: -0.4408

Max Act: 0.2093. Min Act: -0.0000

Data Index: 1066001 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 0.4408. Min Range: -0.4408

Max Act: 0.2229. Min Act: -0.0000

Data Index: 906585 (C4 (Web Text))

Max Activating Token Index: 986