Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2428 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.4572. Min Act: -0.0001

Data Index: 1272932 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.5145. Min Act: -0.0001

Data Index: 20935 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.3631. Min Act: -0.0001

Data Index: 819666 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.4233. Min Act: -0.0000

Data Index: 11999 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.4252. Min Act: -0.0001

Data Index: 1289143 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.4171. Min Act: -0.0001

Data Index: 335398 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.4001. Min Act: -0.0001

Data Index: 1196610 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.4371. Min Act: -0.0001

Data Index: 469311 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.3768. Min Act: -0.0000

Data Index: 669709 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.4271. Min Act: -0.0001

Data Index: 204166 (C4 (Web Text))

Max Activating Token Index: 977

Text #10

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.3906. Min Act: -0.0001

Data Index: 1215781 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.4381. Min Act: -0.0001

Data Index: 791498 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.4285. Min Act: -0.0001

Data Index: 1165211 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.4022. Min Act: -0.0000

Data Index: 1506196 (Python Code)

Max Activating Token Index: 79

Text #14

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.4215. Min Act: -0.0000

Data Index: 922939 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.3520. Min Act: -0.0001

Data Index: 598814 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.3232. Min Act: -0.0001

Data Index: 865635 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.3512. Min Act: -0.0000

Data Index: 958469 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.3350. Min Act: -0.0000

Data Index: 1115892 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 0.5145. Min Range: -0.5145

Max Act: 0.3770. Min Act: -0.0001

Data Index: 321069 (C4 (Web Text))

Max Activating Token Index: 605