Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3260 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.2100. Min Act: -0.0000

Data Index: 89124 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.2036. Min Act: -0.0000

Data Index: 243085 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1939. Min Act: -0.0000

Data Index: 983415 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1963. Min Act: 0.0000

Data Index: 168622 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1942. Min Act: -0.0000

Data Index: 371508 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1744. Min Act: -0.0000

Data Index: 1342191 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1705. Min Act: -0.0000

Data Index: 531125 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1611. Min Act: -0.0000

Data Index: 787164 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1558. Min Act: -0.0000

Data Index: 631704 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1546. Min Act: -0.0000

Data Index: 1313304 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1518. Min Act: -0.0000

Data Index: 1131249 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1443. Min Act: 0.0000

Data Index: 1238354 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1572. Min Act: -0.0000

Data Index: 727169 (C4 (Web Text))

Max Activating Token Index: 788

Text #13

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1471. Min Act: -0.0000

Data Index: 571023 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1507. Min Act: -0.0000

Data Index: 321189 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1446. Min Act: -0.0000

Data Index: 1319961 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1549. Min Act: -0.0000

Data Index: 1076193 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1400. Min Act: -0.0000

Data Index: 887586 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1501. Min Act: -0.0000

Data Index: 466893 (C4 (Web Text))

Max Activating Token Index: 711

Text #19

Max Range: 0.2100. Min Range: -0.2100

Max Act: 0.1376. Min Act: -0.0000

Data Index: 1236138 (C4 (Web Text))

Max Activating Token Index: 383