Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3958 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.3239. Min Act: -0.0000

Data Index: 292873 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.3343. Min Act: -0.0000

Data Index: 155143 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2672. Min Act: -0.0000

Data Index: 825263 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2807. Min Act: -0.0000

Data Index: 153690 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2980. Min Act: -0.0000

Data Index: 203120 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2936. Min Act: -0.0000

Data Index: 569933 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2934. Min Act: -0.0000

Data Index: 14336 (C4 (Web Text))

Max Activating Token Index: 1004

Text #7

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2748. Min Act: -0.0000

Data Index: 1497213 (Python Code)

Max Activating Token Index: 133

Text #8

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2729. Min Act: -0.0000

Data Index: 313350 (C4 (Web Text))

Max Activating Token Index: 619

Text #9

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2699. Min Act: -0.0000

Data Index: 716721 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2746. Min Act: -0.0000

Data Index: 24665 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2425. Min Act: -0.0000

Data Index: 1240769 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2589. Min Act: -0.0000

Data Index: 120644 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2474. Min Act: -0.0000

Data Index: 477451 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2440. Min Act: -0.0000

Data Index: 1476961 (Python Code)

Max Activating Token Index: 164

Text #15

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2470. Min Act: -0.0000

Data Index: 1565873 (Python Code)

Max Activating Token Index: 611

Text #16

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2618. Min Act: -0.0000

Data Index: 1446938 (Python Code)

Max Activating Token Index: 99

Text #17

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2542. Min Act: -0.0000

Data Index: 583836 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2406. Min Act: -0.0000

Data Index: 1327310 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.3343. Min Range: -0.3343

Max Act: 0.2304. Min Act: -0.0000

Data Index: 1153660 (C4 (Web Text))

Max Activating Token Index: 660