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

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

Neuron 765 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: 4.1825. Min Range: -4.1825

Max Act: 4.1825. Min Act: -0.0000

Data Index: 616822 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 4.1825. Min Range: -4.1825

Max Act: 3.7505. Min Act: -0.0000

Data Index: 1152901 (C4 (Web Text))

Max Activating Token Index: 237

Text #2

Max Range: 4.1825. Min Range: -4.1825

Max Act: 3.2402. Min Act: -0.0000

Data Index: 1307301 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 4.1825. Min Range: -4.1825

Max Act: 3.1319. Min Act: -0.0000

Data Index: 892126 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 4.1825. Min Range: -4.1825

Max Act: 3.1643. Min Act: -0.0000

Data Index: 358615 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 4.1825. Min Range: -4.1825

Max Act: 3.1039. Min Act: -0.0000

Data Index: 837259 (C4 (Web Text))

Max Activating Token Index: 954

Text #6

Max Range: 4.1825. Min Range: -4.1825

Max Act: 2.8330. Min Act: -0.0000

Data Index: 53033 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 4.1825. Min Range: -4.1825

Max Act: 2.5333. Min Act: -0.0000

Data Index: 600432 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 4.1825. Min Range: -4.1825

Max Act: 1.8590. Min Act: -0.0000

Data Index: 1271507 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 4.1825. Min Range: -4.1825

Max Act: 2.7646. Min Act: -0.0000

Data Index: 782862 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 4.1825. Min Range: -4.1825

Max Act: 2.3585. Min Act: -0.0000

Data Index: 392251 (C4 (Web Text))

Max Activating Token Index: 585

Text #11

Max Range: 4.1825. Min Range: -4.1825

Max Act: 2.5822. Min Act: -0.0000

Data Index: 481170 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 4.1825. Min Range: -4.1825

Max Act: 2.5729. Min Act: -0.0000

Data Index: 546995 (C4 (Web Text))

Max Activating Token Index: 458

Text #13

Max Range: 4.1825. Min Range: -4.1825

Max Act: 2.5879. Min Act: -0.0000

Data Index: 32694 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 4.1825. Min Range: -4.1825

Max Act: 2.2813. Min Act: -0.0000

Data Index: 508554 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 4.1825. Min Range: -4.1825

Max Act: 2.2287. Min Act: 0.0000

Data Index: 671473 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 4.1825. Min Range: -4.1825

Max Act: 2.2161. Min Act: 0.0000

Data Index: 790204 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 4.1825. Min Range: -4.1825

Max Act: 2.2979. Min Act: -0.0000

Data Index: 1167095 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 4.1825. Min Range: -4.1825

Max Act: 2.1514. Min Act: -0.0000

Data Index: 1352159 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 4.1825. Min Range: -4.1825

Max Act: 2.3460. Min Act: -0.0000

Data Index: 1394860 (Python Code)

Max Activating Token Index: 199