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

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

Neuron 3552 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.2228. Min Act: -0.0001

Data Index: 135525 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1969. Min Act: -0.0001

Data Index: 345736 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.2034. Min Act: -0.0001

Data Index: 690006 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1830. Min Act: -0.0001

Data Index: 113021 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1874. Min Act: -0.0001

Data Index: 1212938 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1757. Min Act: -0.0001

Data Index: 43630 (C4 (Web Text))

Max Activating Token Index: 848

Text #6

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1875. Min Act: -0.0001

Data Index: 1110678 (C4 (Web Text))

Max Activating Token Index: 469

Text #7

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1865. Min Act: -0.0001

Data Index: 1310640 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1709. Min Act: -0.0001

Data Index: 1078672 (C4 (Web Text))

Max Activating Token Index: 818

Text #9

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1668. Min Act: -0.0001

Data Index: 358429 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1762. Min Act: -0.0001

Data Index: 226485 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1661. Min Act: -0.0001

Data Index: 62559 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1667. Min Act: -0.0001

Data Index: 524242 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1643. Min Act: -0.0001

Data Index: 135255 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1587. Min Act: -0.0001

Data Index: 1179227 (C4 (Web Text))

Max Activating Token Index: 94

Text #15

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1584. Min Act: -0.0001

Data Index: 518000 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1576. Min Act: -0.0000

Data Index: 898132 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1481. Min Act: -0.0001

Data Index: 1173825 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1579. Min Act: -0.0001

Data Index: 360916 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1364. Min Act: -0.0001

Data Index: 544783 (C4 (Web Text))

Max Activating Token Index: 881