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

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

Neuron 3598 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7071. Min Range: -3.7071

Max Act: 3.7071. Min Act: -0.0000

Data Index: 365112 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 3.7071. Min Range: -3.7071

Max Act: 3.1255. Min Act: -0.0000

Data Index: 450495 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 3.7071. Min Range: -3.7071

Max Act: 2.9058. Min Act: -0.0001

Data Index: 292768 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 3.7071. Min Range: -3.7071

Max Act: 2.7552. Min Act: -0.0001

Data Index: 808423 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 3.7071. Min Range: -3.7071

Max Act: 2.7258. Min Act: -0.0001

Data Index: 244947 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 3.7071. Min Range: -3.7071

Max Act: 2.5069. Min Act: -0.0001

Data Index: 371870 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 3.7071. Min Range: -3.7071

Max Act: 2.9208. Min Act: -0.0001

Data Index: 343660 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 3.7071. Min Range: -3.7071

Max Act: 3.0839. Min Act: -0.0001

Data Index: 636621 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 3.7071. Min Range: -3.7071

Max Act: 2.3190. Min Act: -0.0001

Data Index: 761821 (C4 (Web Text))

Max Activating Token Index: 377

Text #9

Max Range: 3.7071. Min Range: -3.7071

Max Act: 2.6040. Min Act: -0.0001

Data Index: 105841 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 3.7071. Min Range: -3.7071

Max Act: 2.6766. Min Act: -0.0000

Data Index: 800486 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 3.7071. Min Range: -3.7071

Max Act: 2.7238. Min Act: -0.0001

Data Index: 1133422 (C4 (Web Text))

Max Activating Token Index: 311

Text #12

Max Range: 3.7071. Min Range: -3.7071

Max Act: 2.8110. Min Act: -0.0001

Data Index: 475246 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 3.7071. Min Range: -3.7071

Max Act: 2.5798. Min Act: -0.0001

Data Index: 452424 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 3.7071. Min Range: -3.7071

Max Act: 2.4644. Min Act: -0.0001

Data Index: 249069 (C4 (Web Text))

Max Activating Token Index: 547

Text #15

Max Range: 3.7071. Min Range: -3.7071

Max Act: 2.5115. Min Act: -0.0001

Data Index: 412670 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 3.7071. Min Range: -3.7071

Max Act: 2.6173. Min Act: -0.0000

Data Index: 795205 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 3.7071. Min Range: -3.7071

Max Act: 2.3369. Min Act: -0.0001

Data Index: 71547 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 3.7071. Min Range: -3.7071

Max Act: 2.5420. Min Act: -0.0000

Data Index: 1090775 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 3.7071. Min Range: -3.7071

Max Act: 2.4000. Min Act: -0.0000

Data Index: 692005 (C4 (Web Text))

Max Activating Token Index: 957