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

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

Neuron 5467 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0350. Min Range: -4.0350

Max Act: 4.0350. Min Act: -0.0001

Data Index: 426368 (C4 (Web Text))

Max Activating Token Index: 710

Text #1

Max Range: 4.0350. Min Range: -4.0350

Max Act: 4.0195. Min Act: -0.0001

Data Index: 554154 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 4.0350. Min Range: -4.0350

Max Act: 3.7811. Min Act: -0.0001

Data Index: 458427 (C4 (Web Text))

Max Activating Token Index: 548

Text #3

Max Range: 4.0350. Min Range: -4.0350

Max Act: 3.7685. Min Act: -0.0001

Data Index: 239361 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 4.0350. Min Range: -4.0350

Max Act: 3.6113. Min Act: -0.0001

Data Index: 1261331 (C4 (Web Text))

Max Activating Token Index: 452

Text #5

Max Range: 4.0350. Min Range: -4.0350

Max Act: 3.5099. Min Act: -0.0000

Data Index: 1199017 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 4.0350. Min Range: -4.0350

Max Act: 3.4930. Min Act: -0.0001

Data Index: 388875 (C4 (Web Text))

Max Activating Token Index: 641

Text #7

Max Range: 4.0350. Min Range: -4.0350

Max Act: 3.4439. Min Act: -0.0001

Data Index: 1105351 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 4.0350. Min Range: -4.0350

Max Act: 3.5698. Min Act: -0.0001

Data Index: 519335 (C4 (Web Text))

Max Activating Token Index: 524

Text #9

Max Range: 4.0350. Min Range: -4.0350

Max Act: 3.5425. Min Act: -0.0000

Data Index: 639909 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 4.0350. Min Range: -4.0350

Max Act: 3.6976. Min Act: -0.0000

Data Index: 205611 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 4.0350. Min Range: -4.0350

Max Act: 3.4576. Min Act: -0.0001

Data Index: 481331 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 4.0350. Min Range: -4.0350

Max Act: 3.3530. Min Act: -0.0001

Data Index: 1154007 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 4.0350. Min Range: -4.0350

Max Act: 3.3421. Min Act: -0.0000

Data Index: 929272 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 4.0350. Min Range: -4.0350

Max Act: 3.4838. Min Act: -0.0000

Data Index: 749088 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 4.0350. Min Range: -4.0350

Max Act: 3.3218. Min Act: -0.0000

Data Index: 727329 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 4.0350. Min Range: -4.0350

Max Act: 3.4158. Min Act: -0.0001

Data Index: 1235951 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 4.0350. Min Range: -4.0350

Max Act: 3.1172. Min Act: -0.0000

Data Index: 771695 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 4.0350. Min Range: -4.0350

Max Act: 2.9782. Min Act: -0.0000

Data Index: 1147855 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 4.0350. Min Range: -4.0350

Max Act: 3.0191. Min Act: -0.0000

Data Index: 228444 (C4 (Web Text))

Max Activating Token Index: 443