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

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

Neuron 989 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.2101. Min Act: -0.0001

Data Index: 269441 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1681. Min Act: -0.0001

Data Index: 751717 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1916. Min Act: -0.0001

Data Index: 1067956 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1654. Min Act: -0.0001

Data Index: 20 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1674. Min Act: -0.0001

Data Index: 1179525 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1890. Min Act: -0.0001

Data Index: 456226 (C4 (Web Text))

Max Activating Token Index: 253

Text #6

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1705. Min Act: -0.0001

Data Index: 54204 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1697. Min Act: -0.0000

Data Index: 143031 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1580. Min Act: -0.0001

Data Index: 1018813 (C4 (Web Text))

Max Activating Token Index: 858

Text #9

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1486. Min Act: -0.0001

Data Index: 627656 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1567. Min Act: -0.0001

Data Index: 1055370 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1777. Min Act: -0.0001

Data Index: 902678 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1492. Min Act: -0.0001

Data Index: 209388 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1378. Min Act: -0.0001

Data Index: 253241 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1506. Min Act: -0.0001

Data Index: 1109396 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1497. Min Act: -0.0001

Data Index: 576985 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1472. Min Act: -0.0001

Data Index: 452308 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1547. Min Act: -0.0001

Data Index: 690911 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1734. Min Act: -0.0001

Data Index: 1207099 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.2101. Min Range: -0.2101

Max Act: 0.1361. Min Act: -0.0001

Data Index: 445553 (C4 (Web Text))

Max Activating Token Index: 170