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

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

Neuron 3058 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.2466. Min Range: -8.2466

Max Act: 8.2466. Min Act: -0.0000

Data Index: 947546 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 8.2466. Min Range: -8.2466

Max Act: 8.0550. Min Act: -0.0000

Data Index: 823063 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 8.2466. Min Range: -8.2466

Max Act: 7.5358. Min Act: -0.0000

Data Index: 627837 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 8.2466. Min Range: -8.2466

Max Act: 7.7264. Min Act: -0.0000

Data Index: 441219 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 8.2466. Min Range: -8.2466

Max Act: 7.6866. Min Act: -0.0000

Data Index: 299839 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 8.2466. Min Range: -8.2466

Max Act: 7.9025. Min Act: -0.0000

Data Index: 446836 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 8.2466. Min Range: -8.2466

Max Act: 6.4853. Min Act: -0.0000

Data Index: 102436 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 8.2466. Min Range: -8.2466

Max Act: 7.3895. Min Act: -0.0000

Data Index: 1158582 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 8.2466. Min Range: -8.2466

Max Act: 7.3060. Min Act: -0.0000

Data Index: 552965 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 8.2466. Min Range: -8.2466

Max Act: 7.1223. Min Act: -0.0000

Data Index: 50389 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 8.2466. Min Range: -8.2466

Max Act: 7.0342. Min Act: -0.0000

Data Index: 300635 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 8.2466. Min Range: -8.2466

Max Act: 6.8267. Min Act: -0.0000

Data Index: 950464 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 8.2466. Min Range: -8.2466

Max Act: 7.5175. Min Act: -0.0000

Data Index: 392702 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 8.2466. Min Range: -8.2466

Max Act: 7.4755. Min Act: -0.0000

Data Index: 295000 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 8.2466. Min Range: -8.2466

Max Act: 7.3132. Min Act: -0.0000

Data Index: 893777 (C4 (Web Text))

Max Activating Token Index: 596

Text #15

Max Range: 8.2466. Min Range: -8.2466

Max Act: 6.7241. Min Act: -0.0000

Data Index: 926106 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 8.2466. Min Range: -8.2466

Max Act: 7.2085. Min Act: -0.0000

Data Index: 1021513 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 8.2466. Min Range: -8.2466

Max Act: 7.2100. Min Act: -0.0000

Data Index: 514853 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 8.2466. Min Range: -8.2466

Max Act: 7.1947. Min Act: -0.0000

Data Index: 538503 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 8.2466. Min Range: -8.2466

Max Act: 6.9992. Min Act: -0.0000

Data Index: 1092062 (C4 (Web Text))

Max Activating Token Index: 359