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

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

Neuron 5421 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: 2.1583. Min Range: -2.1583

Max Act: 2.1583. Min Act: -0.0000

Data Index: 500955 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 2.1583. Min Range: -2.1583

Max Act: 2.0097. Min Act: -0.0000

Data Index: 1607260 (Python Code)

Max Activating Token Index: 615

Text #2

Max Range: 2.1583. Min Range: -2.1583

Max Act: 2.0673. Min Act: -0.0000

Data Index: 1402075 (Python Code)

Max Activating Token Index: 740

Text #3

Max Range: 2.1583. Min Range: -2.1583

Max Act: 1.9131. Min Act: -0.0000

Data Index: 1530995 (Python Code)

Max Activating Token Index: 823

Text #4

Max Range: 2.1583. Min Range: -2.1583

Max Act: 1.7446. Min Act: -0.0000

Data Index: 1286735 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 2.1583. Min Range: -2.1583

Max Act: 1.8278. Min Act: -0.0000

Data Index: 289432 (C4 (Web Text))

Max Activating Token Index: 263

Text #6

Max Range: 2.1583. Min Range: -2.1583

Max Act: 1.7416. Min Act: -0.0000

Data Index: 1492160 (Python Code)

Max Activating Token Index: 1003

Text #7

Max Range: 2.1583. Min Range: -2.1583

Max Act: 1.8346. Min Act: -0.0000

Data Index: 626105 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 2.1583. Min Range: -2.1583

Max Act: 1.7537. Min Act: -0.0000

Data Index: 521861 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 2.1583. Min Range: -2.1583

Max Act: 1.6593. Min Act: -0.0000

Data Index: 1481410 (Python Code)

Max Activating Token Index: 752

Text #10

Max Range: 2.1583. Min Range: -2.1583

Max Act: 1.6480. Min Act: -0.0000

Data Index: 814007 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 2.1583. Min Range: -2.1583

Max Act: 1.6361. Min Act: -0.0000

Data Index: 847637 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 2.1583. Min Range: -2.1583

Max Act: 1.5842. Min Act: -0.0000

Data Index: 1412682 (Python Code)

Max Activating Token Index: 198

Text #13

Max Range: 2.1583. Min Range: -2.1583

Max Act: 1.6388. Min Act: -0.0000

Data Index: 853454 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 2.1583. Min Range: -2.1583

Max Act: 1.7740. Min Act: -0.0000

Data Index: 1427740 (Python Code)

Max Activating Token Index: 958

Text #15

Max Range: 2.1583. Min Range: -2.1583

Max Act: 1.6243. Min Act: -0.0000

Data Index: 912592 (C4 (Web Text))

Max Activating Token Index: 633

Text #16

Max Range: 2.1583. Min Range: -2.1583

Max Act: 1.4626. Min Act: -0.0000

Data Index: 1394905 (Python Code)

Max Activating Token Index: 330

Text #17

Max Range: 2.1583. Min Range: -2.1583

Max Act: 1.5173. Min Act: -0.0000

Data Index: 1118939 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 2.1583. Min Range: -2.1583

Max Act: 1.5703. Min Act: -0.0000

Data Index: 1180413 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 2.1583. Min Range: -2.1583

Max Act: 1.5678. Min Act: -0.0000

Data Index: 989420 (C4 (Web Text))

Max Activating Token Index: 839