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

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

Neuron 6142 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: 1.9363. Min Range: -1.9363

Max Act: 1.8402. Min Act: -0.0001

Data Index: 98346 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 1.9363. Min Range: -1.9363

Max Act: 1.9363. Min Act: -0.0001

Data Index: 638489 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 1.9363. Min Range: -1.9363

Max Act: 1.4904. Min Act: -0.0001

Data Index: 922161 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 1.9363. Min Range: -1.9363

Max Act: 1.4758. Min Act: -0.0001

Data Index: 1639592 (Python Code)

Max Activating Token Index: 401

Text #4

Max Range: 1.9363. Min Range: -1.9363

Max Act: 1.4248. Min Act: -0.0001

Data Index: 1490616 (Python Code)

Max Activating Token Index: 225

Text #5

Max Range: 1.9363. Min Range: -1.9363

Max Act: 1.3369. Min Act: -0.0001

Data Index: 261614 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 1.9363. Min Range: -1.9363

Max Act: 1.4086. Min Act: -0.0001

Data Index: 705452 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 1.9363. Min Range: -1.9363

Max Act: 1.3271. Min Act: -0.0001

Data Index: 327331 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 1.9363. Min Range: -1.9363

Max Act: 1.3509. Min Act: -0.0001

Data Index: 1594845 (Python Code)

Max Activating Token Index: 308

Text #9

Max Range: 1.9363. Min Range: -1.9363

Max Act: 1.3895. Min Act: -0.0001

Data Index: 855916 (C4 (Web Text))

Max Activating Token Index: 16

Text #10

Max Range: 1.9363. Min Range: -1.9363

Max Act: 1.4092. Min Act: -0.0001

Data Index: 1576600 (Python Code)

Max Activating Token Index: 187

Text #11

Max Range: 1.9363. Min Range: -1.9363

Max Act: 1.3583. Min Act: -0.0001

Data Index: 1628176 (Python Code)

Max Activating Token Index: 314

Text #12

Max Range: 1.9363. Min Range: -1.9363

Max Act: 1.3887. Min Act: -0.0001

Data Index: 223912 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 1.9363. Min Range: -1.9363

Max Act: 1.2302. Min Act: -0.0001

Data Index: 1403890 (Python Code)

Max Activating Token Index: 631

Text #14

Max Range: 1.9363. Min Range: -1.9363

Max Act: 1.2519. Min Act: -0.0001

Data Index: 1554144 (Python Code)

Max Activating Token Index: 774

Text #15

Max Range: 1.9363. Min Range: -1.9363

Max Act: 1.2945. Min Act: -0.0001

Data Index: 243540 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 1.9363. Min Range: -1.9363

Max Act: 1.3129. Min Act: -0.0001

Data Index: 949078 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 1.9363. Min Range: -1.9363

Max Act: 1.2721. Min Act: -0.0001

Data Index: 396784 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 1.9363. Min Range: -1.9363

Max Act: 1.2855. Min Act: -0.0001

Data Index: 1028608 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 1.9363. Min Range: -1.9363

Max Act: 1.2375. Min Act: -0.0001

Data Index: 1312025 (C4 (Web Text))

Max Activating Token Index: 265