Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 773 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0461. Min Range: -1.0461

Max Act: 1.0461. Min Act: -0.0000

Data Index: 325794 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 1.0461. Min Range: -1.0461

Max Act: 1.0205. Min Act: -0.0000

Data Index: 1089776 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 1.0461. Min Range: -1.0461

Max Act: 1.0116. Min Act: -0.0000

Data Index: 542975 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.9512. Min Act: -0.0000

Data Index: 1077629 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.8684. Min Act: -0.0000

Data Index: 1060431 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.9014. Min Act: -0.0000

Data Index: 1062158 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.9026. Min Act: -0.0000

Data Index: 329355 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.8387. Min Act: -0.0000

Data Index: 468074 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.8387. Min Act: -0.0000

Data Index: 626919 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.7916. Min Act: -0.0000

Data Index: 1221340 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.8102. Min Act: -0.0000

Data Index: 824602 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.8140. Min Act: -0.0000

Data Index: 27423 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.7952. Min Act: -0.0000

Data Index: 424030 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.8406. Min Act: -0.0000

Data Index: 659749 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.7549. Min Act: -0.0000

Data Index: 839679 (C4 (Web Text))

Max Activating Token Index: 144

Text #15

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.7697. Min Act: -0.0000

Data Index: 908794 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.8140. Min Act: -0.0000

Data Index: 172597 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.7552. Min Act: -0.0000

Data Index: 1060027 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.7224. Min Act: -0.0000

Data Index: 533852 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 1.0461. Min Range: -1.0461

Max Act: 0.7275. Min Act: -0.0000

Data Index: 1356437 (C4 (Web Text))

Max Activating Token Index: 361