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

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

Neuron 4454 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9295. Min Range: -1.9295

Max Act: 1.6278. Min Act: -0.0000

Data Index: 1544317 (Python Code)

Max Activating Token Index: 762

Text #1

Max Range: 1.9295. Min Range: -1.9295

Max Act: 1.6394. Min Act: -0.0000

Data Index: 973448 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 1.9295. Min Range: -1.9295

Max Act: 1.6160. Min Act: -0.0000

Data Index: 803844 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 1.9295. Min Range: -1.9295

Max Act: 1.7888. Min Act: -0.0000

Data Index: 1632117 (Python Code)

Max Activating Token Index: 96

Text #4

Max Range: 1.9295. Min Range: -1.9295

Max Act: 1.6596. Min Act: -0.0000

Data Index: 1162585 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 1.9295. Min Range: -1.9295

Max Act: 1.5435. Min Act: -0.0000

Data Index: 1449039 (Python Code)

Max Activating Token Index: 914

Text #6

Max Range: 1.9295. Min Range: -1.9295

Max Act: 1.9295. Min Act: -0.0000

Data Index: 1542159 (Python Code)

Max Activating Token Index: 671

Text #7

Max Range: 1.9295. Min Range: -1.9295

Max Act: 1.5838. Min Act: -0.0000

Data Index: 1548886 (Python Code)

Max Activating Token Index: 670

Text #8

Max Range: 1.9295. Min Range: -1.9295

Max Act: 1.6778. Min Act: -0.0000

Data Index: 1606903 (Python Code)

Max Activating Token Index: 188

Text #9

Max Range: 1.9295. Min Range: -1.9295

Max Act: 1.4991. Min Act: -0.0000

Data Index: 1400181 (Python Code)

Max Activating Token Index: 111

Text #10

Max Range: 1.9295. Min Range: -1.9295

Max Act: 1.7810. Min Act: -0.0000

Data Index: 1627301 (Python Code)

Max Activating Token Index: 764

Text #11

Max Range: 1.9295. Min Range: -1.9295

Max Act: 1.5743. Min Act: -0.0000

Data Index: 822865 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 1.9295. Min Range: -1.9295

Max Act: 1.5411. Min Act: -0.0000

Data Index: 1552551 (Python Code)

Max Activating Token Index: 234

Text #13

Max Range: 1.9295. Min Range: -1.9295

Max Act: 1.5118. Min Act: -0.0000

Data Index: 1600085 (Python Code)

Max Activating Token Index: 284

Text #14

Max Range: 1.9295. Min Range: -1.9295

Max Act: 1.4579. Min Act: -0.0000

Data Index: 394833 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 1.9295. Min Range: -1.9295

Max Act: 1.5279. Min Act: -0.0000

Data Index: 1523935 (Python Code)

Max Activating Token Index: 24

Text #16

Max Range: 1.9295. Min Range: -1.9295

Max Act: 1.4011. Min Act: -0.0000

Data Index: 1602042 (Python Code)

Max Activating Token Index: 609

Text #17

Max Range: 1.9295. Min Range: -1.9295

Max Act: 1.5525. Min Act: -0.0000

Data Index: 1231297 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 1.9295. Min Range: -1.9295

Max Act: 1.4078. Min Act: -0.0000

Data Index: 298736 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 1.9295. Min Range: -1.9295

Max Act: 1.4912. Min Act: -0.0000

Data Index: 1503361 (Python Code)

Max Activating Token Index: 16