Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2461 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 3.1575. Min Range: -3.1575

Max Act: 3.1078. Min Act: -0.0001

Data Index: 850172 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 3.1575. Min Range: -3.1575

Max Act: 3.1575. Min Act: -0.0001

Data Index: 781521 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 3.1575. Min Range: -3.1575

Max Act: 3.0627. Min Act: -0.0001

Data Index: 558478 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 3.1575. Min Range: -3.1575

Max Act: 3.0743. Min Act: -0.0001

Data Index: 665093 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 3.1575. Min Range: -3.1575

Max Act: 3.0091. Min Act: -0.0001

Data Index: 1106244 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 3.1575. Min Range: -3.1575

Max Act: 3.1093. Min Act: -0.0001

Data Index: 361403 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 3.1575. Min Range: -3.1575

Max Act: 2.9601. Min Act: -0.0001

Data Index: 140872 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 3.1575. Min Range: -3.1575

Max Act: 2.8668. Min Act: -0.0001

Data Index: 721391 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 3.1575. Min Range: -3.1575

Max Act: 2.9326. Min Act: -0.0001

Data Index: 1213233 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 3.1575. Min Range: -3.1575

Max Act: 2.9723. Min Act: -0.0001

Data Index: 466017 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 3.1575. Min Range: -3.1575

Max Act: 2.9279. Min Act: -0.0001

Data Index: 88477 (C4 (Web Text))

Max Activating Token Index: 385

Text #11

Max Range: 3.1575. Min Range: -3.1575

Max Act: 2.9801. Min Act: -0.0001

Data Index: 47851 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 3.1575. Min Range: -3.1575

Max Act: 2.7047. Min Act: -0.0001

Data Index: 652731 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 3.1575. Min Range: -3.1575

Max Act: 2.9099. Min Act: -0.0001

Data Index: 966712 (C4 (Web Text))

Max Activating Token Index: 41

Text #14

Max Range: 3.1575. Min Range: -3.1575

Max Act: 2.9857. Min Act: -0.0001

Data Index: 932185 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 3.1575. Min Range: -3.1575

Max Act: 2.8257. Min Act: -0.0001

Data Index: 247335 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 3.1575. Min Range: -3.1575

Max Act: 2.8174. Min Act: -0.0001

Data Index: 958704 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 3.1575. Min Range: -3.1575

Max Act: 2.8089. Min Act: -0.0001

Data Index: 817464 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 3.1575. Min Range: -3.1575

Max Act: 2.8655. Min Act: -0.0001

Data Index: 1072086 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 3.1575. Min Range: -3.1575

Max Act: 2.7280. Min Act: -0.0001

Data Index: 646749 (C4 (Web Text))

Max Activating Token Index: 101