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

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

Neuron 3812 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5616. Min Range: -1.5616

Max Act: 1.5616. Min Act: -0.0000

Data Index: 1173059 (C4 (Web Text))

Max Activating Token Index: 252

Text #1

Max Range: 1.5616. Min Range: -1.5616

Max Act: 0.8985. Min Act: -0.0000

Data Index: 997232 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 1.5616. Min Range: -1.5616

Max Act: 0.7897. Min Act: -0.0000

Data Index: 140424 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 1.5616. Min Range: -1.5616

Max Act: 0.8181. Min Act: -0.0000

Data Index: 561913 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 1.5616. Min Range: -1.5616

Max Act: 0.7806. Min Act: -0.0000

Data Index: 77047 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 1.5616. Min Range: -1.5616

Max Act: 0.7125. Min Act: -0.0000

Data Index: 1079455 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 1.5616. Min Range: -1.5616

Max Act: 0.6356. Min Act: -0.0000

Data Index: 743107 (C4 (Web Text))

Max Activating Token Index: 775

Text #7

Max Range: 1.5616. Min Range: -1.5616

Max Act: 0.6661. Min Act: -0.0000

Data Index: 266367 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 1.5616. Min Range: -1.5616

Max Act: 0.6442. Min Act: -0.0000

Data Index: 709235 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 1.5616. Min Range: -1.5616

Max Act: 0.6089. Min Act: -0.0000

Data Index: 837686 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 1.5616. Min Range: -1.5616

Max Act: 0.6141. Min Act: -0.0000

Data Index: 429614 (C4 (Web Text))

Max Activating Token Index: 412

Text #11

Max Range: 1.5616. Min Range: -1.5616

Max Act: 0.5906. Min Act: -0.0000

Data Index: 198295 (C4 (Web Text))

Max Activating Token Index: 681

Text #12

Max Range: 1.5616. Min Range: -1.5616

Max Act: 0.6131. Min Act: 0.0000

Data Index: 1383873 (Python Code)

Max Activating Token Index: 617

Text #13

Max Range: 1.5616. Min Range: -1.5616

Max Act: 0.6240. Min Act: 0.0000

Data Index: 289338 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 1.5616. Min Range: -1.5616

Max Act: 0.6077. Min Act: -0.0000

Data Index: 457681 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 1.5616. Min Range: -1.5616

Max Act: 0.5887. Min Act: -0.0000

Data Index: 1222716 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 1.5616. Min Range: -1.5616

Max Act: 0.5655. Min Act: -0.0000

Data Index: 736410 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 1.5616. Min Range: -1.5616

Max Act: 0.5315. Min Act: -0.0000

Data Index: 1202949 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 1.5616. Min Range: -1.5616

Max Act: 0.5715. Min Act: -0.0000

Data Index: 401033 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 1.5616. Min Range: -1.5616

Max Act: 0.5322. Min Act: -0.0000

Data Index: 1189408 (C4 (Web Text))

Max Activating Token Index: 526