Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3855 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.5649. Min Act: -0.0001

Data Index: 619875 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.5073. Min Act: -0.0000

Data Index: 179814 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.4406. Min Act: -0.0001

Data Index: 1496868 (Python Code)

Max Activating Token Index: 871

Text #3

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.4162. Min Act: -0.0001

Data Index: 1595758 (Python Code)

Max Activating Token Index: 221

Text #4

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.3932. Min Act: -0.0000

Data Index: 1557351 (Python Code)

Max Activating Token Index: 302

Text #5

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.3736. Min Act: -0.0001

Data Index: 1391112 (Python Code)

Max Activating Token Index: 738

Text #6

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.3815. Min Act: -0.0000

Data Index: 365960 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.3791. Min Act: -0.0001

Data Index: 1367500 (Python Code)

Max Activating Token Index: 690

Text #8

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.3660. Min Act: -0.0001

Data Index: 1577628 (Python Code)

Max Activating Token Index: 920

Text #9

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.3637. Min Act: -0.0000

Data Index: 528039 (C4 (Web Text))

Max Activating Token Index: 206

Text #10

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.3708. Min Act: -0.0001

Data Index: 1533910 (Python Code)

Max Activating Token Index: 80

Text #11

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.3714. Min Act: -0.0000

Data Index: 1638047 (Python Code)

Max Activating Token Index: 86

Text #12

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.3550. Min Act: -0.0000

Data Index: 188008 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.3271. Min Act: -0.0001

Data Index: 1283335 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.3248. Min Act: -0.0000

Data Index: 305317 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.3251. Min Act: -0.0000

Data Index: 989051 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.3351. Min Act: -0.0001

Data Index: 1639240 (Python Code)

Max Activating Token Index: 768

Text #17

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.3320. Min Act: -0.0001

Data Index: 1491009 (Python Code)

Max Activating Token Index: 437

Text #18

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.3318. Min Act: -0.0001

Data Index: 1634600 (Python Code)

Max Activating Token Index: 542

Text #19

Max Range: 0.5649. Min Range: -0.5649

Max Act: 0.3190. Min Act: -0.0000

Data Index: 1340238 (C4 (Web Text))

Max Activating Token Index: 354