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

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

Neuron 1580 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7913. Min Range: -4.7913

Max Act: 4.6518. Min Act: -0.0000

Data Index: 1330361 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 4.7913. Min Range: -4.7913

Max Act: 4.7913. Min Act: -0.0000

Data Index: 682386 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 4.7913. Min Range: -4.7913

Max Act: 3.4915. Min Act: -0.0000

Data Index: 947385 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 4.7913. Min Range: -4.7913

Max Act: 3.4855. Min Act: -0.0000

Data Index: 230506 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 4.7913. Min Range: -4.7913

Max Act: 3.6841. Min Act: -0.0000

Data Index: 490452 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 4.7913. Min Range: -4.7913

Max Act: 3.8342. Min Act: -0.0000

Data Index: 1389987 (Python Code)

Max Activating Token Index: 1001

Text #6

Max Range: 4.7913. Min Range: -4.7913

Max Act: 3.6417. Min Act: -0.0000

Data Index: 965785 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 4.7913. Min Range: -4.7913

Max Act: 3.4160. Min Act: -0.0000

Data Index: 1623533 (Python Code)

Max Activating Token Index: 158

Text #8

Max Range: 4.7913. Min Range: -4.7913

Max Act: 3.3402. Min Act: -0.0000

Data Index: 1309644 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 4.7913. Min Range: -4.7913

Max Act: 3.3013. Min Act: -0.0000

Data Index: 1456292 (Python Code)

Max Activating Token Index: 69

Text #10

Max Range: 4.7913. Min Range: -4.7913

Max Act: 3.2562. Min Act: -0.0000

Data Index: 1112628 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 4.7913. Min Range: -4.7913

Max Act: 3.2484. Min Act: -0.0000

Data Index: 1508082 (Python Code)

Max Activating Token Index: 705

Text #12

Max Range: 4.7913. Min Range: -4.7913

Max Act: 3.1677. Min Act: -0.0000

Data Index: 728349 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 4.7913. Min Range: -4.7913

Max Act: 3.4375. Min Act: -0.0000

Data Index: 946452 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 4.7913. Min Range: -4.7913

Max Act: 3.2473. Min Act: -0.0000

Data Index: 1543973 (Python Code)

Max Activating Token Index: 566

Text #15

Max Range: 4.7913. Min Range: -4.7913

Max Act: 3.1197. Min Act: -0.0000

Data Index: 328262 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 4.7913. Min Range: -4.7913

Max Act: 3.2379. Min Act: -0.0000

Data Index: 1506825 (Python Code)

Max Activating Token Index: 680

Text #17

Max Range: 4.7913. Min Range: -4.7913

Max Act: 2.9475. Min Act: -0.0000

Data Index: 1581248 (Python Code)

Max Activating Token Index: 625

Text #18

Max Range: 4.7913. Min Range: -4.7913

Max Act: 3.1018. Min Act: -0.0000

Data Index: 1498937 (Python Code)

Max Activating Token Index: 933

Text #19

Max Range: 4.7913. Min Range: -4.7913

Max Act: 3.2417. Min Act: -0.0000

Data Index: 1545883 (Python Code)

Max Activating Token Index: 176