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

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

Neuron 214 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: 2.5155. Min Range: -2.5155

Max Act: 2.5155. Min Act: -0.0000

Data Index: 18898 (C4 (Web Text))

Max Activating Token Index: 250

Text #1

Max Range: 2.5155. Min Range: -2.5155

Max Act: 1.7582. Min Act: -0.0000

Data Index: 599745 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 2.5155. Min Range: -2.5155

Max Act: 1.5741. Min Act: -0.0000

Data Index: 683046 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 2.5155. Min Range: -2.5155

Max Act: 1.4175. Min Act: -0.0000

Data Index: 744564 (C4 (Web Text))

Max Activating Token Index: 551

Text #4

Max Range: 2.5155. Min Range: -2.5155

Max Act: 1.4672. Min Act: -0.0000

Data Index: 216119 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 2.5155. Min Range: -2.5155

Max Act: 1.5347. Min Act: -0.0000

Data Index: 1139308 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 2.5155. Min Range: -2.5155

Max Act: 1.4600. Min Act: -0.0000

Data Index: 874212 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 2.5155. Min Range: -2.5155

Max Act: 1.4481. Min Act: -0.0000

Data Index: 1242200 (C4 (Web Text))

Max Activating Token Index: 649

Text #8

Max Range: 2.5155. Min Range: -2.5155

Max Act: 1.4448. Min Act: -0.0000

Data Index: 829268 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 2.5155. Min Range: -2.5155

Max Act: 1.3342. Min Act: -0.0000

Data Index: 193415 (C4 (Web Text))

Max Activating Token Index: 596

Text #10

Max Range: 2.5155. Min Range: -2.5155

Max Act: 1.2642. Min Act: -0.0000

Data Index: 1179262 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 2.5155. Min Range: -2.5155

Max Act: 1.2536. Min Act: -0.0000

Data Index: 883652 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 2.5155. Min Range: -2.5155

Max Act: 1.3152. Min Act: -0.0000

Data Index: 491188 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 2.5155. Min Range: -2.5155

Max Act: 1.2217. Min Act: -0.0000

Data Index: 500512 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 2.5155. Min Range: -2.5155

Max Act: 1.2882. Min Act: -0.0000

Data Index: 392438 (C4 (Web Text))

Max Activating Token Index: 262

Text #15

Max Range: 2.5155. Min Range: -2.5155

Max Act: 1.3716. Min Act: -0.0000

Data Index: 404767 (C4 (Web Text))

Max Activating Token Index: 468

Text #16

Max Range: 2.5155. Min Range: -2.5155

Max Act: 1.4368. Min Act: -0.0000

Data Index: 1018578 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 2.5155. Min Range: -2.5155

Max Act: 1.2912. Min Act: -0.0000

Data Index: 124819 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 2.5155. Min Range: -2.5155

Max Act: 1.2758. Min Act: -0.0000

Data Index: 71337 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 2.5155. Min Range: -2.5155

Max Act: 1.3446. Min Act: -0.0000

Data Index: 34540 (C4 (Web Text))

Max Activating Token Index: 173