Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2259 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.8237. Min Act: -0.0001

Data Index: 583295 (C4 (Web Text))

Max Activating Token Index: 437

Text #1

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.8182. Min Act: -0.0001

Data Index: 226573 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.7211. Min Act: -0.0001

Data Index: 491981 (C4 (Web Text))

Max Activating Token Index: 285

Text #3

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.8096. Min Act: -0.0001

Data Index: 139082 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.7683. Min Act: -0.0001

Data Index: 1290085 (C4 (Web Text))

Max Activating Token Index: 454

Text #5

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.7332. Min Act: -0.0001

Data Index: 335686 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.7000. Min Act: -0.0001

Data Index: 36186 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.7401. Min Act: -0.0001

Data Index: 196553 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.7059. Min Act: -0.0001

Data Index: 318547 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.7348. Min Act: -0.0001

Data Index: 423493 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.7217. Min Act: -0.0001

Data Index: 777134 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6945. Min Act: -0.0001

Data Index: 40536 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6874. Min Act: -0.0001

Data Index: 30877 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.7280. Min Act: -0.0001

Data Index: 568495 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.7257. Min Act: -0.0001

Data Index: 252507 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6999. Min Act: -0.0001

Data Index: 1359152 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.7258. Min Act: -0.0001

Data Index: 1299933 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.7335. Min Act: -0.0001

Data Index: 1210306 (C4 (Web Text))

Max Activating Token Index: 765

Text #18

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6481. Min Act: -0.0001

Data Index: 1145781 (C4 (Web Text))

Max Activating Token Index: 198

Text #19

Max Range: 0.8237. Min Range: -0.8237

Max Act: 0.6995. Min Act: -0.0001

Data Index: 265250 (C4 (Web Text))

Max Activating Token Index: 437