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

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

Neuron 2821 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: 0.1808. Min Range: -0.1808

Max Act: 0.1808. Min Act: -0.0001

Data Index: 1542737 (Python Code)

Max Activating Token Index: 438

Text #1

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1784. Min Act: -0.0001

Data Index: 733143 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1617. Min Act: -0.0001

Data Index: 527853 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1620. Min Act: -0.0001

Data Index: 1144805 (C4 (Web Text))

Max Activating Token Index: 160

Text #4

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1605. Min Act: -0.0001

Data Index: 525985 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1702. Min Act: -0.0001

Data Index: 218784 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1461. Min Act: -0.0001

Data Index: 295460 (C4 (Web Text))

Max Activating Token Index: 277

Text #7

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1501. Min Act: -0.0001

Data Index: 1283302 (C4 (Web Text))

Max Activating Token Index: 934

Text #8

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1419. Min Act: -0.0001

Data Index: 1212314 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1393. Min Act: -0.0001

Data Index: 354552 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1432. Min Act: -0.0001

Data Index: 40891 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1412. Min Act: -0.0001

Data Index: 143212 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1460. Min Act: -0.0001

Data Index: 783132 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1527. Min Act: -0.0001

Data Index: 1317273 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1400. Min Act: -0.0001

Data Index: 958179 (C4 (Web Text))

Max Activating Token Index: 551

Text #15

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1382. Min Act: -0.0001

Data Index: 410827 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1460. Min Act: -0.0001

Data Index: 124094 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1402. Min Act: -0.0001

Data Index: 1139371 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1349. Min Act: -0.0001

Data Index: 750352 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 0.1808. Min Range: -0.1808

Max Act: 0.1392. Min Act: -0.0001

Data Index: 865231 (C4 (Web Text))

Max Activating Token Index: 88