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

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

Neuron 3348 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: 4.9136. Min Range: -4.9136

Max Act: 4.9136. Min Act: -0.0000

Data Index: 990302 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 4.9136. Min Range: -4.9136

Max Act: 3.8171. Min Act: -0.0000

Data Index: 790231 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 4.9136. Min Range: -4.9136

Max Act: 3.6411. Min Act: -0.0000

Data Index: 1358774 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 4.9136. Min Range: -4.9136

Max Act: 3.2398. Min Act: -0.0000

Data Index: 1285249 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 4.9136. Min Range: -4.9136

Max Act: 3.1791. Min Act: -0.0000

Data Index: 1127019 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 4.9136. Min Range: -4.9136

Max Act: 2.9904. Min Act: -0.0000

Data Index: 925186 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 4.9136. Min Range: -4.9136

Max Act: 2.4245. Min Act: -0.0000

Data Index: 1104217 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 4.9136. Min Range: -4.9136

Max Act: 2.4444. Min Act: -0.0000

Data Index: 522025 (C4 (Web Text))

Max Activating Token Index: 435

Text #8

Max Range: 4.9136. Min Range: -4.9136

Max Act: 2.5612. Min Act: -0.0000

Data Index: 843522 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 4.9136. Min Range: -4.9136

Max Act: 2.5266. Min Act: -0.0000

Data Index: 967663 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 4.9136. Min Range: -4.9136

Max Act: 2.3647. Min Act: -0.0000

Data Index: 1015113 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 4.9136. Min Range: -4.9136

Max Act: 2.4825. Min Act: -0.0000

Data Index: 783140 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 4.9136. Min Range: -4.9136

Max Act: 2.2875. Min Act: -0.0000

Data Index: 1134883 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 4.9136. Min Range: -4.9136

Max Act: 2.2544. Min Act: -0.0000

Data Index: 500068 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 4.9136. Min Range: -4.9136

Max Act: 2.2462. Min Act: -0.0000

Data Index: 58847 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 4.9136. Min Range: -4.9136

Max Act: 2.1924. Min Act: -0.0000

Data Index: 34510 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 4.9136. Min Range: -4.9136

Max Act: 2.1395. Min Act: -0.0000

Data Index: 1198655 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 4.9136. Min Range: -4.9136

Max Act: 2.1379. Min Act: -0.0000

Data Index: 924123 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 4.9136. Min Range: -4.9136

Max Act: 2.0123. Min Act: -0.0000

Data Index: 1048525 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 4.9136. Min Range: -4.9136

Max Act: 2.0989. Min Act: -0.0000

Data Index: 707597 (C4 (Web Text))

Max Activating Token Index: 930