Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2553 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 7.3619. Min Range: -7.3619

Max Act: 7.3619. Min Act: -0.0000

Data Index: 427245 (C4 (Web Text))

Max Activating Token Index: 982

Text #1

Max Range: 7.3619. Min Range: -7.3619

Max Act: 6.8584. Min Act: -0.0000

Data Index: 773010 (C4 (Web Text))

Max Activating Token Index: 933

Text #2

Max Range: 7.3619. Min Range: -7.3619

Max Act: 6.4747. Min Act: -0.0000

Data Index: 1539428 (Python Code)

Max Activating Token Index: 95

Text #3

Max Range: 7.3619. Min Range: -7.3619

Max Act: 6.2443. Min Act: -0.0000

Data Index: 1437278 (Python Code)

Max Activating Token Index: 127

Text #4

Max Range: 7.3619. Min Range: -7.3619

Max Act: 6.3278. Min Act: -0.0000

Data Index: 932997 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 7.3619. Min Range: -7.3619

Max Act: 6.1595. Min Act: -0.0000

Data Index: 1394224 (Python Code)

Max Activating Token Index: 693

Text #6

Max Range: 7.3619. Min Range: -7.3619

Max Act: 5.8973. Min Act: -0.0000

Data Index: 1325483 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 7.3619. Min Range: -7.3619

Max Act: 6.0696. Min Act: -0.0000

Data Index: 1161393 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 7.3619. Min Range: -7.3619

Max Act: 6.2580. Min Act: -0.0000

Data Index: 337124 (C4 (Web Text))

Max Activating Token Index: 390

Text #9

Max Range: 7.3619. Min Range: -7.3619

Max Act: 5.7549. Min Act: -0.0000

Data Index: 1601587 (Python Code)

Max Activating Token Index: 134

Text #10

Max Range: 7.3619. Min Range: -7.3619

Max Act: 6.0441. Min Act: -0.0000

Data Index: 1000764 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 7.3619. Min Range: -7.3619

Max Act: 5.6922. Min Act: -0.0000

Data Index: 1485079 (Python Code)

Max Activating Token Index: 576

Text #12

Max Range: 7.3619. Min Range: -7.3619

Max Act: 5.8249. Min Act: -0.0000

Data Index: 355712 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 7.3619. Min Range: -7.3619

Max Act: 5.7885. Min Act: -0.0000

Data Index: 1445952 (Python Code)

Max Activating Token Index: 133

Text #14

Max Range: 7.3619. Min Range: -7.3619

Max Act: 5.5108. Min Act: -0.0000

Data Index: 1453845 (Python Code)

Max Activating Token Index: 549

Text #15

Max Range: 7.3619. Min Range: -7.3619

Max Act: 5.5342. Min Act: -0.0000

Data Index: 1398428 (Python Code)

Max Activating Token Index: 590

Text #16

Max Range: 7.3619. Min Range: -7.3619

Max Act: 5.6612. Min Act: -0.0000

Data Index: 1429761 (Python Code)

Max Activating Token Index: 75

Text #17

Max Range: 7.3619. Min Range: -7.3619

Max Act: 5.4646. Min Act: -0.0000

Data Index: 1656713 (Python Code)

Max Activating Token Index: 431

Text #18

Max Range: 7.3619. Min Range: -7.3619

Max Act: 5.6353. Min Act: -0.0000

Data Index: 1487393 (Python Code)

Max Activating Token Index: 130

Text #19

Max Range: 7.3619. Min Range: -7.3619

Max Act: 5.7902. Min Act: -0.0000

Data Index: 1502338 (Python Code)

Max Activating Token Index: 878