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

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

Neuron 3197 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.5367. Min Act: -0.0000

Data Index: 1633260 (Python Code)

Max Activating Token Index: 25

Text #1

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.4737. Min Act: -0.0000

Data Index: 1622399 (Python Code)

Max Activating Token Index: 774

Text #2

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.5220. Min Act: -0.0000

Data Index: 1470224 (Python Code)

Max Activating Token Index: 417

Text #3

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.5083. Min Act: -0.0000

Data Index: 1459237 (Python Code)

Max Activating Token Index: 75

Text #4

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.4674. Min Act: -0.0000

Data Index: 1628935 (Python Code)

Max Activating Token Index: 268

Text #5

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.5139. Min Act: -0.0000

Data Index: 675997 (C4 (Web Text))

Max Activating Token Index: 997

Text #6

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.4852. Min Act: -0.0000

Data Index: 1459068 (Python Code)

Max Activating Token Index: 77

Text #7

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.4348. Min Act: -0.0000

Data Index: 1552892 (Python Code)

Max Activating Token Index: 836

Text #8

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.4788. Min Act: -0.0000

Data Index: 959296 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.3866. Min Act: -0.0000

Data Index: 1460852 (Python Code)

Max Activating Token Index: 339

Text #10

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.4479. Min Act: -0.0000

Data Index: 704365 (C4 (Web Text))

Max Activating Token Index: 170

Text #11

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.4464. Min Act: -0.0000

Data Index: 1642955 (Python Code)

Max Activating Token Index: 533

Text #12

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.4422. Min Act: -0.0000

Data Index: 1499218 (Python Code)

Max Activating Token Index: 723

Text #13

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.4262. Min Act: -0.0000

Data Index: 1223735 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.4070. Min Act: -0.0000

Data Index: 1648058 (Python Code)

Max Activating Token Index: 347

Text #15

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.4244. Min Act: -0.0000

Data Index: 1570496 (Python Code)

Max Activating Token Index: 907

Text #16

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.4357. Min Act: -0.0000

Data Index: 1524948 (Python Code)

Max Activating Token Index: 127

Text #17

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.4371. Min Act: -0.0000

Data Index: 1651268 (Python Code)

Max Activating Token Index: 598

Text #18

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.4355. Min Act: -0.0000

Data Index: 1493234 (Python Code)

Max Activating Token Index: 536

Text #19

Max Range: 0.5367. Min Range: -0.5367

Max Act: 0.3964. Min Act: -0.0000

Data Index: 1373903 (Python Code)

Max Activating Token Index: 177