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

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

Neuron 5217 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0238. Min Range: -2.0238

Max Act: 1.9899. Min Act: -0.0000

Data Index: 1456232 (Python Code)

Max Activating Token Index: 926

Text #1

Max Range: 2.0238. Min Range: -2.0238

Max Act: 2.0238. Min Act: -0.0000

Data Index: 801459 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 2.0238. Min Range: -2.0238

Max Act: 1.5517. Min Act: -0.0000

Data Index: 1078849 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 2.0238. Min Range: -2.0238

Max Act: 1.5762. Min Act: -0.0000

Data Index: 26933 (C4 (Web Text))

Max Activating Token Index: 465

Text #4

Max Range: 2.0238. Min Range: -2.0238

Max Act: 1.5468. Min Act: -0.0000

Data Index: 1425382 (Python Code)

Max Activating Token Index: 114

Text #5

Max Range: 2.0238. Min Range: -2.0238

Max Act: 1.6394. Min Act: -0.0000

Data Index: 1475427 (Python Code)

Max Activating Token Index: 95

Text #6

Max Range: 2.0238. Min Range: -2.0238

Max Act: 1.5469. Min Act: -0.0000

Data Index: 1616416 (Python Code)

Max Activating Token Index: 455

Text #7

Max Range: 2.0238. Min Range: -2.0238

Max Act: 1.5621. Min Act: -0.0000

Data Index: 1418911 (Python Code)

Max Activating Token Index: 305

Text #8

Max Range: 2.0238. Min Range: -2.0238

Max Act: 1.5385. Min Act: -0.0000

Data Index: 633075 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 2.0238. Min Range: -2.0238

Max Act: 1.5222. Min Act: -0.0000

Data Index: 881938 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 2.0238. Min Range: -2.0238

Max Act: 1.5002. Min Act: -0.0000

Data Index: 1408584 (Python Code)

Max Activating Token Index: 688

Text #11

Max Range: 2.0238. Min Range: -2.0238

Max Act: 1.6458. Min Act: -0.0000

Data Index: 880198 (C4 (Web Text))

Max Activating Token Index: 645

Text #12

Max Range: 2.0238. Min Range: -2.0238

Max Act: 1.4665. Min Act: -0.0000

Data Index: 1415315 (Python Code)

Max Activating Token Index: 668

Text #13

Max Range: 2.0238. Min Range: -2.0238

Max Act: 1.5410. Min Act: -0.0000

Data Index: 1634579 (Python Code)

Max Activating Token Index: 659

Text #14

Max Range: 2.0238. Min Range: -2.0238

Max Act: 1.4562. Min Act: -0.0000

Data Index: 1648554 (Python Code)

Max Activating Token Index: 428

Text #15

Max Range: 2.0238. Min Range: -2.0238

Max Act: 1.4388. Min Act: -0.0000

Data Index: 1567774 (Python Code)

Max Activating Token Index: 173

Text #16

Max Range: 2.0238. Min Range: -2.0238

Max Act: 1.3620. Min Act: -0.0000

Data Index: 128653 (C4 (Web Text))

Max Activating Token Index: 537

Text #17

Max Range: 2.0238. Min Range: -2.0238

Max Act: 1.2841. Min Act: -0.0000

Data Index: 1608874 (Python Code)

Max Activating Token Index: 986

Text #18

Max Range: 2.0238. Min Range: -2.0238

Max Act: 1.3461. Min Act: -0.0000

Data Index: 1585508 (Python Code)

Max Activating Token Index: 242

Text #19

Max Range: 2.0238. Min Range: -2.0238

Max Act: 1.3884. Min Act: -0.0000

Data Index: 739413 (C4 (Web Text))

Max Activating Token Index: 892