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

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

Neuron 1775 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.7333. Min Act: -0.0001

Data Index: 841742 (C4 (Web Text))

Max Activating Token Index: 159

Text #1

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.8430. Min Act: -0.0001

Data Index: 1316584 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.6524. Min Act: -0.0001

Data Index: 1262366 (C4 (Web Text))

Max Activating Token Index: 327

Text #3

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.5273. Min Act: -0.0000

Data Index: 409216 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.6191. Min Act: -0.0001

Data Index: 560563 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.5238. Min Act: -0.0000

Data Index: 1085408 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.4042. Min Act: -0.0001

Data Index: 665294 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.4096. Min Act: -0.0000

Data Index: 1063130 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.4607. Min Act: -0.0000

Data Index: 362099 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.3890. Min Act: -0.0001

Data Index: 701210 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.2287. Min Act: -0.0000

Data Index: 809960 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.1077. Min Act: -0.0001

Data Index: 841479 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.2088. Min Act: -0.0000

Data Index: 512750 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.2077. Min Act: -0.0001

Data Index: 52105 (C4 (Web Text))

Max Activating Token Index: 946

Text #14

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.1830. Min Act: -0.0001

Data Index: 1059838 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.1883. Min Act: -0.0000

Data Index: 53950 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.2371. Min Act: -0.0001

Data Index: 1012187 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.2901. Min Act: -0.0001

Data Index: 553572 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.2361. Min Act: -0.0000

Data Index: 414640 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 2.8430. Min Range: -2.8430

Max Act: 2.1042. Min Act: -0.0000

Data Index: 278563 (C4 (Web Text))

Max Activating Token Index: 581