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

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

Neuron 3069 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5198. Min Range: -4.5198

Max Act: 4.5198. Min Act: -0.0000

Data Index: 50431 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 4.5198. Min Range: -4.5198

Max Act: 4.0761. Min Act: -0.0000

Data Index: 178950 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 4.5198. Min Range: -4.5198

Max Act: 3.6391. Min Act: -0.0000

Data Index: 572760 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 4.5198. Min Range: -4.5198

Max Act: 3.5375. Min Act: -0.0000

Data Index: 182779 (C4 (Web Text))

Max Activating Token Index: 854

Text #4

Max Range: 4.5198. Min Range: -4.5198

Max Act: 3.4870. Min Act: -0.0000

Data Index: 199539 (C4 (Web Text))

Max Activating Token Index: 316

Text #5

Max Range: 4.5198. Min Range: -4.5198

Max Act: 3.3799. Min Act: -0.0000

Data Index: 1110739 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 4.5198. Min Range: -4.5198

Max Act: 3.1828. Min Act: -0.0000

Data Index: 81742 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 4.5198. Min Range: -4.5198

Max Act: 3.1001. Min Act: -0.0000

Data Index: 514058 (C4 (Web Text))

Max Activating Token Index: 276

Text #8

Max Range: 4.5198. Min Range: -4.5198

Max Act: 3.0953. Min Act: -0.0000

Data Index: 196315 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 4.5198. Min Range: -4.5198

Max Act: 3.0215. Min Act: -0.0000

Data Index: 368703 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 4.5198. Min Range: -4.5198

Max Act: 2.9930. Min Act: -0.0000

Data Index: 747244 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 4.5198. Min Range: -4.5198

Max Act: 3.1179. Min Act: -0.0000

Data Index: 1014808 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 4.5198. Min Range: -4.5198

Max Act: 2.9465. Min Act: -0.0000

Data Index: 341730 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 4.5198. Min Range: -4.5198

Max Act: 2.9319. Min Act: -0.0000

Data Index: 673842 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 4.5198. Min Range: -4.5198

Max Act: 2.9189. Min Act: -0.0000

Data Index: 1093126 (C4 (Web Text))

Max Activating Token Index: 810

Text #15

Max Range: 4.5198. Min Range: -4.5198

Max Act: 2.9684. Min Act: -0.0000

Data Index: 1049029 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 4.5198. Min Range: -4.5198

Max Act: 2.8260. Min Act: -0.0000

Data Index: 716325 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 4.5198. Min Range: -4.5198

Max Act: 2.8104. Min Act: -0.0000

Data Index: 316033 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 4.5198. Min Range: -4.5198

Max Act: 2.8072. Min Act: -0.0000

Data Index: 120128 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 4.5198. Min Range: -4.5198

Max Act: 2.7592. Min Act: -0.0000

Data Index: 95651 (C4 (Web Text))

Max Activating Token Index: 283