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

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

Neuron 1194 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0592. Min Act: -0.0003

Data Index: 1396535 (Python Code)

Max Activating Token Index: 89

Text #1

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0546. Min Act: -0.0003

Data Index: 902151 (C4 (Web Text))

Max Activating Token Index: 641

Text #2

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0536. Min Act: -0.0003

Data Index: 862776 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0471. Min Act: -0.0003

Data Index: 16435 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0493. Min Act: -0.0003

Data Index: 1650209 (Python Code)

Max Activating Token Index: 549

Text #5

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0517. Min Act: -0.0003

Data Index: 1391650 (Python Code)

Max Activating Token Index: 939

Text #6

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0507. Min Act: -0.0003

Data Index: 1572434 (Python Code)

Max Activating Token Index: 416

Text #7

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0458. Min Act: -0.0003

Data Index: 1461002 (Python Code)

Max Activating Token Index: 906

Text #8

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0504. Min Act: -0.0003

Data Index: 1460245 (Python Code)

Max Activating Token Index: 356

Text #9

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0462. Min Act: -0.0003

Data Index: 1405578 (Python Code)

Max Activating Token Index: 411

Text #10

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0452. Min Act: -0.0003

Data Index: 689292 (C4 (Web Text))

Max Activating Token Index: 856

Text #11

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0467. Min Act: -0.0003

Data Index: 1630298 (Python Code)

Max Activating Token Index: 355

Text #12

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0440. Min Act: -0.0003

Data Index: 469441 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0471. Min Act: -0.0003

Data Index: 1496722 (Python Code)

Max Activating Token Index: 662

Text #14

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0450. Min Act: -0.0003

Data Index: 1461428 (Python Code)

Max Activating Token Index: 126

Text #15

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0438. Min Act: -0.0003

Data Index: 1033399 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0472. Min Act: -0.0003

Data Index: 1450786 (Python Code)

Max Activating Token Index: 271

Text #17

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0440. Min Act: -0.0003

Data Index: 920028 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0424. Min Act: -0.0003

Data Index: 567443 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0439. Min Act: -0.0003

Data Index: 1411559 (Python Code)

Max Activating Token Index: 642