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

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

Neuron 5922 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.8803. Min Act: -0.0000

Data Index: 101115 (C4 (Web Text))

Max Activating Token Index: 679

Text #1

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.7270. Min Act: -0.0000

Data Index: 357712 (C4 (Web Text))

Max Activating Token Index: 875

Text #2

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.6413. Min Act: -0.0000

Data Index: 428952 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.6091. Min Act: -0.0000

Data Index: 499342 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.6032. Min Act: -0.0000

Data Index: 546039 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.5804. Min Act: -0.0000

Data Index: 1306304 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.5916. Min Act: -0.0000

Data Index: 621809 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.5882. Min Act: -0.0000

Data Index: 586409 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.5623. Min Act: -0.0000

Data Index: 1252193 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.5382. Min Act: -0.0000

Data Index: 932678 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.5670. Min Act: -0.0000

Data Index: 148800 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.5544. Min Act: -0.0000

Data Index: 1188259 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.5085. Min Act: -0.0000

Data Index: 429586 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.4903. Min Act: -0.0000

Data Index: 147675 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.4648. Min Act: -0.0000

Data Index: 961435 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.4227. Min Act: -0.0000

Data Index: 152838 (C4 (Web Text))

Max Activating Token Index: 396

Text #16

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.4079. Min Act: -0.0000

Data Index: 477248 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.3849. Min Act: -0.0000

Data Index: 81583 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.3701. Min Act: -0.0000

Data Index: 7508 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 0.8803. Min Range: -0.8803

Max Act: 0.3778. Min Act: -0.0000

Data Index: 32020 (C4 (Web Text))

Max Activating Token Index: 542