Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 134 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0596. Min Act: -0.0002

Data Index: 1123302 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0583. Min Act: -0.0002

Data Index: 410852 (C4 (Web Text))

Max Activating Token Index: 124

Text #2

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0556. Min Act: -0.0002

Data Index: 136420 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0556. Min Act: -0.0002

Data Index: 703644 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0542. Min Act: -0.0001

Data Index: 451631 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1220220 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0534. Min Act: -0.0001

Data Index: 845247 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0533. Min Act: -0.0002

Data Index: 931885 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0525. Min Act: -0.0002

Data Index: 706678 (C4 (Web Text))

Max Activating Token Index: 947

Text #9

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0499. Min Act: -0.0001

Data Index: 428187 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0510. Min Act: -0.0002

Data Index: 740909 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0510. Min Act: -0.0002

Data Index: 1112563 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0507. Min Act: -0.0002

Data Index: 305878 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0509. Min Act: -0.0002

Data Index: 1068898 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0494. Min Act: -0.0002

Data Index: 606681 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0492. Min Act: -0.0002

Data Index: 604928 (C4 (Web Text))

Max Activating Token Index: 115

Text #16

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0486. Min Act: -0.0001

Data Index: 449069 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0497. Min Act: -0.0001

Data Index: 115459 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0487. Min Act: -0.0002

Data Index: 791822 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 0.0596. Min Range: -0.0596

Max Act: 0.0485. Min Act: -0.0002

Data Index: 606986 (C4 (Web Text))

Max Activating Token Index: 352