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

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

Neuron 3374 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0591. Min Range: -1.0591

Max Act: 1.0591. Min Act: -0.0000

Data Index: 526671 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.8506. Min Act: -0.0000

Data Index: 625066 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.9289. Min Act: -0.0000

Data Index: 591346 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.8498. Min Act: -0.0000

Data Index: 589223 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.7924. Min Act: -0.0000

Data Index: 602915 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.7916. Min Act: -0.0000

Data Index: 542388 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.7585. Min Act: -0.0000

Data Index: 22017 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.7922. Min Act: -0.0000

Data Index: 350582 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.7854. Min Act: -0.0000

Data Index: 100198 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.8259. Min Act: -0.0000

Data Index: 231575 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.7522. Min Act: -0.0000

Data Index: 775680 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.7709. Min Act: -0.0000

Data Index: 1309014 (C4 (Web Text))

Max Activating Token Index: 942

Text #12

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.7514. Min Act: -0.0000

Data Index: 40097 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.7254. Min Act: -0.0000

Data Index: 233230 (C4 (Web Text))

Max Activating Token Index: 214

Text #14

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.7890. Min Act: -0.0000

Data Index: 1304428 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.7346. Min Act: -0.0000

Data Index: 684354 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.7154. Min Act: -0.0000

Data Index: 420862 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.7296. Min Act: -0.0000

Data Index: 1099037 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.6994. Min Act: -0.0000

Data Index: 1210774 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 1.0591. Min Range: -1.0591

Max Act: 0.6900. Min Act: -0.0000

Data Index: 555489 (C4 (Web Text))

Max Activating Token Index: 452