Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1523 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3015. Min Range: -2.3015

Max Act: 2.3015. Min Act: -0.0000

Data Index: 1110964 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 2.3015. Min Range: -2.3015

Max Act: 2.0601. Min Act: -0.0000

Data Index: 795640 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 2.3015. Min Range: -2.3015

Max Act: 1.6739. Min Act: -0.0000

Data Index: 276484 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 2.3015. Min Range: -2.3015

Max Act: 1.0485. Min Act: -0.0000

Data Index: 263330 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 2.3015. Min Range: -2.3015

Max Act: 1.0067. Min Act: -0.0000

Data Index: 736536 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 2.3015. Min Range: -2.3015

Max Act: 0.9806. Min Act: -0.0000

Data Index: 209540 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 2.3015. Min Range: -2.3015

Max Act: 0.8335. Min Act: -0.0000

Data Index: 1458844 (Python Code)

Max Activating Token Index: 803

Text #7

Max Range: 2.3015. Min Range: -2.3015

Max Act: 0.8637. Min Act: -0.0000

Data Index: 321399 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 2.3015. Min Range: -2.3015

Max Act: 0.8516. Min Act: -0.0000

Data Index: 1469802 (Python Code)

Max Activating Token Index: 968

Text #9

Max Range: 2.3015. Min Range: -2.3015

Max Act: 0.8483. Min Act: -0.0000

Data Index: 316368 (C4 (Web Text))

Max Activating Token Index: 1007

Text #10

Max Range: 2.3015. Min Range: -2.3015

Max Act: 0.6619. Min Act: 0.0000

Data Index: 1364749 (Python Code)

Max Activating Token Index: 39

Text #11

Max Range: 2.3015. Min Range: -2.3015

Max Act: 0.7087. Min Act: -0.0000

Data Index: 1123802 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 2.3015. Min Range: -2.3015

Max Act: 0.7388. Min Act: -0.0000

Data Index: 1435563 (Python Code)

Max Activating Token Index: 562

Text #13

Max Range: 2.3015. Min Range: -2.3015

Max Act: 0.7649. Min Act: 0.0000

Data Index: 1518512 (Python Code)

Max Activating Token Index: 249

Text #14

Max Range: 2.3015. Min Range: -2.3015

Max Act: 0.7602. Min Act: -0.0000

Data Index: 1549229 (Python Code)

Max Activating Token Index: 489

Text #15

Max Range: 2.3015. Min Range: -2.3015

Max Act: 0.6837. Min Act: -0.0000

Data Index: 108691 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 2.3015. Min Range: -2.3015

Max Act: 0.7210. Min Act: -0.0000

Data Index: 1497111 (Python Code)

Max Activating Token Index: 852

Text #17

Max Range: 2.3015. Min Range: -2.3015

Max Act: 0.7466. Min Act: -0.0000

Data Index: 1613329 (Python Code)

Max Activating Token Index: 534

Text #18

Max Range: 2.3015. Min Range: -2.3015

Max Act: 0.7095. Min Act: -0.0000

Data Index: 1448905 (Python Code)

Max Activating Token Index: 559

Text #19

Max Range: 2.3015. Min Range: -2.3015

Max Act: 0.7191. Min Act: -0.0000

Data Index: 1420825 (Python Code)

Max Activating Token Index: 756