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

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

Neuron 3202 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.6916. Min Act: -0.0000

Data Index: 1555214 (Python Code)

Max Activating Token Index: 131

Text #1

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.6497. Min Act: -0.0000

Data Index: 1606957 (Python Code)

Max Activating Token Index: 149

Text #2

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.6366. Min Act: -0.0000

Data Index: 1504499 (Python Code)

Max Activating Token Index: 736

Text #3

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5967. Min Act: -0.0000

Data Index: 1036980 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5584. Min Act: -0.0000

Data Index: 1378565 (Python Code)

Max Activating Token Index: 367

Text #5

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.6069. Min Act: -0.0000

Data Index: 1579474 (Python Code)

Max Activating Token Index: 726

Text #6

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.6221. Min Act: -0.0000

Data Index: 272118 (C4 (Web Text))

Max Activating Token Index: 823

Text #7

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5705. Min Act: -0.0000

Data Index: 612776 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5478. Min Act: -0.0000

Data Index: 1426824 (Python Code)

Max Activating Token Index: 26

Text #9

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5100. Min Act: -0.0000

Data Index: 17195 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5235. Min Act: -0.0000

Data Index: 351543 (C4 (Web Text))

Max Activating Token Index: 1011

Text #11

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.4792. Min Act: -0.0000

Data Index: 1441515 (Python Code)

Max Activating Token Index: 217

Text #12

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.4920. Min Act: -0.0000

Data Index: 500034 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.4632. Min Act: -0.0000

Data Index: 1173797 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.4914. Min Act: -0.0000

Data Index: 1645604 (Python Code)

Max Activating Token Index: 548

Text #15

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.4384. Min Act: -0.0000

Data Index: 1549560 (Python Code)

Max Activating Token Index: 118

Text #16

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.4445. Min Act: -0.0000

Data Index: 133497 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.4367. Min Act: -0.0000

Data Index: 131378 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.4367. Min Act: -0.0000

Data Index: 392681 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.4450. Min Act: -0.0000

Data Index: 35779 (C4 (Web Text))

Max Activating Token Index: 580