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

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

Neuron 5345 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1223. Min Range: -2.1223

Max Act: 2.1223. Min Act: -0.0000

Data Index: 174751 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 2.1223. Min Range: -2.1223

Max Act: 1.6753. Min Act: -0.0000

Data Index: 630104 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 2.1223. Min Range: -2.1223

Max Act: 1.4855. Min Act: -0.0000

Data Index: 378038 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 2.1223. Min Range: -2.1223

Max Act: 1.4844. Min Act: -0.0000

Data Index: 201471 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 2.1223. Min Range: -2.1223

Max Act: 1.4859. Min Act: -0.0000

Data Index: 1252332 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 2.1223. Min Range: -2.1223

Max Act: 1.3725. Min Act: -0.0000

Data Index: 110647 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 2.1223. Min Range: -2.1223

Max Act: 1.3594. Min Act: -0.0000

Data Index: 8508 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 2.1223. Min Range: -2.1223

Max Act: 1.3371. Min Act: -0.0000

Data Index: 215149 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 2.1223. Min Range: -2.1223

Max Act: 1.4007. Min Act: -0.0000

Data Index: 446635 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 2.1223. Min Range: -2.1223

Max Act: 1.2937. Min Act: -0.0000

Data Index: 604326 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 2.1223. Min Range: -2.1223

Max Act: 1.3686. Min Act: -0.0000

Data Index: 469690 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 2.1223. Min Range: -2.1223

Max Act: 1.2826. Min Act: -0.0000

Data Index: 1275034 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 2.1223. Min Range: -2.1223

Max Act: 1.3425. Min Act: -0.0000

Data Index: 905184 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 2.1223. Min Range: -2.1223

Max Act: 1.0596. Min Act: -0.0000

Data Index: 274347 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 2.1223. Min Range: -2.1223

Max Act: 1.2231. Min Act: -0.0000

Data Index: 472837 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 2.1223. Min Range: -2.1223

Max Act: 1.2608. Min Act: -0.0000

Data Index: 1087257 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 2.1223. Min Range: -2.1223

Max Act: 1.1797. Min Act: -0.0000

Data Index: 241781 (C4 (Web Text))

Max Activating Token Index: 429

Text #17

Max Range: 2.1223. Min Range: -2.1223

Max Act: 1.1113. Min Act: -0.0000

Data Index: 437477 (C4 (Web Text))

Max Activating Token Index: 267

Text #18

Max Range: 2.1223. Min Range: -2.1223

Max Act: 1.1731. Min Act: -0.0000

Data Index: 661294 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 2.1223. Min Range: -2.1223

Max Act: 1.1627. Min Act: -0.0000

Data Index: 498400 (C4 (Web Text))

Max Activating Token Index: 167