Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3840 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.7385. Min Act: -0.0001

Data Index: 60052 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.6650. Min Act: -0.0001

Data Index: 975519 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.7365. Min Act: -0.0001

Data Index: 886477 (C4 (Web Text))

Max Activating Token Index: 878

Text #3

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.5386. Min Act: -0.0001

Data Index: 1169885 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.5340. Min Act: -0.0001

Data Index: 816300 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.5012. Min Act: -0.0001

Data Index: 119007 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.5499. Min Act: -0.0001

Data Index: 1019922 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.4846. Min Act: -0.0001

Data Index: 633927 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.4740. Min Act: -0.0000

Data Index: 927905 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.5660. Min Act: -0.0001

Data Index: 76282 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.5640. Min Act: -0.0001

Data Index: 1077069 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.5089. Min Act: -0.0001

Data Index: 541900 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.4606. Min Act: -0.0001

Data Index: 146714 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.4576. Min Act: -0.0001

Data Index: 589487 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.4860. Min Act: -0.0001

Data Index: 1371962 (Python Code)

Max Activating Token Index: 566

Text #15

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.4005. Min Act: -0.0001

Data Index: 1442234 (Python Code)

Max Activating Token Index: 108

Text #16

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.4728. Min Act: -0.0001

Data Index: 1489919 (Python Code)

Max Activating Token Index: 609

Text #17

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.3302. Min Act: -0.0001

Data Index: 874392 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.3505. Min Act: -0.0001

Data Index: 457749 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 1.7385. Min Range: -1.7385

Max Act: 1.3832. Min Act: -0.0001

Data Index: 1306924 (C4 (Web Text))

Max Activating Token Index: 241