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

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

Neuron 306 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1482. Min Act: -0.0001

Data Index: 537634 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1474. Min Act: -0.0001

Data Index: 29235 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1335. Min Act: -0.0001

Data Index: 260366 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1252. Min Act: -0.0001

Data Index: 537240 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1136. Min Act: -0.0001

Data Index: 1062930 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1234. Min Act: -0.0001

Data Index: 1309710 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1173. Min Act: -0.0001

Data Index: 1098946 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1187. Min Act: -0.0001

Data Index: 277038 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1065. Min Act: -0.0001

Data Index: 1272557 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1025. Min Act: -0.0001

Data Index: 232451 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1010. Min Act: -0.0001

Data Index: 954640 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1063. Min Act: -0.0001

Data Index: 1223661 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.1014. Min Act: -0.0001

Data Index: 745694 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0942. Min Act: -0.0001

Data Index: 59239 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0935. Min Act: -0.0001

Data Index: 1031741 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0957. Min Act: -0.0001

Data Index: 650924 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0916. Min Act: -0.0001

Data Index: 348662 (C4 (Web Text))

Max Activating Token Index: 895

Text #17

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0981. Min Act: -0.0001

Data Index: 1344548 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0906. Min Act: -0.0001

Data Index: 673644 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 0.1482. Min Range: -0.1482

Max Act: 0.0874. Min Act: -0.0001

Data Index: 228909 (C4 (Web Text))

Max Activating Token Index: 908