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

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

Neuron 2099 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.8049. Min Act: -0.0001

Data Index: 653792 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.6577. Min Act: -0.0001

Data Index: 320470 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.7424. Min Act: -0.0001

Data Index: 894433 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.7450. Min Act: -0.0001

Data Index: 1073967 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.5289. Min Act: -0.0001

Data Index: 918791 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.5343. Min Act: -0.0001

Data Index: 868479 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.5951. Min Act: -0.0001

Data Index: 480579 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.5522. Min Act: -0.0001

Data Index: 476253 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.5058. Min Act: -0.0001

Data Index: 706053 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.4687. Min Act: -0.0001

Data Index: 990969 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.4976. Min Act: -0.0001

Data Index: 779960 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.4989. Min Act: -0.0001

Data Index: 81005 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.4260. Min Act: -0.0001

Data Index: 137467 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.5534. Min Act: -0.0001

Data Index: 532264 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.4767. Min Act: -0.0001

Data Index: 1072034 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.4169. Min Act: -0.0001

Data Index: 857645 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.4338. Min Act: -0.0001

Data Index: 780528 (C4 (Web Text))

Max Activating Token Index: 446

Text #17

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.4298. Min Act: -0.0001

Data Index: 570903 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.4670. Min Act: -0.0001

Data Index: 1313548 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 1.8049. Min Range: -1.8049

Max Act: 1.5579. Min Act: -0.0001

Data Index: 1213623 (C4 (Web Text))

Max Activating Token Index: 854