Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1604 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 3.2960. Min Range: -3.2960

Max Act: 3.2960. Min Act: -0.0001

Data Index: 967028 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 3.2960. Min Range: -3.2960

Max Act: 2.1435. Min Act: -0.0001

Data Index: 97354 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 3.2960. Min Range: -3.2960

Max Act: 2.3596. Min Act: -0.0001

Data Index: 386287 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 3.2960. Min Range: -3.2960

Max Act: 1.9707. Min Act: -0.0001

Data Index: 425447 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 3.2960. Min Range: -3.2960

Max Act: 1.9269. Min Act: -0.0001

Data Index: 575541 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 3.2960. Min Range: -3.2960

Max Act: 2.0199. Min Act: -0.0001

Data Index: 978297 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 3.2960. Min Range: -3.2960

Max Act: 1.9497. Min Act: -0.0001

Data Index: 480342 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 3.2960. Min Range: -3.2960

Max Act: 1.7525. Min Act: -0.0001

Data Index: 838348 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 3.2960. Min Range: -3.2960

Max Act: 1.7541. Min Act: -0.0001

Data Index: 1177405 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 3.2960. Min Range: -3.2960

Max Act: 1.6261. Min Act: -0.0001

Data Index: 1298963 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 3.2960. Min Range: -3.2960

Max Act: 1.5804. Min Act: -0.0001

Data Index: 1224543 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 3.2960. Min Range: -3.2960

Max Act: 1.4725. Min Act: -0.0001

Data Index: 550312 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 3.2960. Min Range: -3.2960

Max Act: 1.3809. Min Act: -0.0001

Data Index: 215449 (C4 (Web Text))

Max Activating Token Index: 1014

Text #13

Max Range: 3.2960. Min Range: -3.2960

Max Act: 1.4728. Min Act: -0.0001

Data Index: 759467 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 3.2960. Min Range: -3.2960

Max Act: 1.4563. Min Act: -0.0001

Data Index: 663132 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 3.2960. Min Range: -3.2960

Max Act: 1.2534. Min Act: -0.0001

Data Index: 216914 (C4 (Web Text))

Max Activating Token Index: 574

Text #16

Max Range: 3.2960. Min Range: -3.2960

Max Act: 1.3867. Min Act: -0.0001

Data Index: 1076490 (C4 (Web Text))

Max Activating Token Index: 164

Text #17

Max Range: 3.2960. Min Range: -3.2960

Max Act: 1.4499. Min Act: -0.0001

Data Index: 806602 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 3.2960. Min Range: -3.2960

Max Act: 1.4422. Min Act: -0.0001

Data Index: 1286680 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 3.2960. Min Range: -3.2960

Max Act: 1.4711. Min Act: -0.0001

Data Index: 484237 (C4 (Web Text))

Max Activating Token Index: 739