Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2040 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.2483. Min Act: -0.0001

Data Index: 282117 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.2494. Min Act: -0.0001

Data Index: 664420 (C4 (Web Text))

Max Activating Token Index: 839

Text #2

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.2302. Min Act: -0.0001

Data Index: 858475 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.2252. Min Act: -0.0001

Data Index: 642280 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.1695. Min Act: -0.0001

Data Index: 1189813 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.2031. Min Act: -0.0001

Data Index: 361884 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.1964. Min Act: -0.0001

Data Index: 182340 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.1958. Min Act: -0.0001

Data Index: 750838 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.1685. Min Act: -0.0001

Data Index: 140314 (C4 (Web Text))

Max Activating Token Index: 337

Text #9

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.1793. Min Act: -0.0001

Data Index: 1197755 (C4 (Web Text))

Max Activating Token Index: 560

Text #10

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.1891. Min Act: -0.0001

Data Index: 1004379 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.1755. Min Act: -0.0001

Data Index: 1194284 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.2002. Min Act: -0.0001

Data Index: 480098 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.1645. Min Act: -0.0001

Data Index: 222411 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.1481. Min Act: -0.0001

Data Index: 1163816 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.1472. Min Act: -0.0001

Data Index: 248666 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.1556. Min Act: -0.0001

Data Index: 1224041 (C4 (Web Text))

Max Activating Token Index: 892

Text #17

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.1479. Min Act: -0.0001

Data Index: 400142 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.1639. Min Act: -0.0001

Data Index: 61699 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 0.2494. Min Range: -0.2494

Max Act: 0.1350. Min Act: -0.0001

Data Index: 1239164 (C4 (Web Text))

Max Activating Token Index: 821