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

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

Neuron 3684 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.4614. Min Act: -0.0000

Data Index: 150605 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.4424. Min Act: -0.0000

Data Index: 623591 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.3382. Min Act: -0.0000

Data Index: 381783 (C4 (Web Text))

Max Activating Token Index: 759

Text #3

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2907. Min Act: -0.0000

Data Index: 149478 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2913. Min Act: -0.0000

Data Index: 1390830 (Python Code)

Max Activating Token Index: 593

Text #5

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2713. Min Act: -0.0000

Data Index: 1576677 (Python Code)

Max Activating Token Index: 460

Text #6

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2649. Min Act: -0.0000

Data Index: 1440867 (Python Code)

Max Activating Token Index: 419

Text #7

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2641. Min Act: -0.0000

Data Index: 1318126 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2545. Min Act: -0.0000

Data Index: 1147803 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2540. Min Act: -0.0000

Data Index: 165284 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2342. Min Act: -0.0000

Data Index: 1062351 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2350. Min Act: -0.0000

Data Index: 1455578 (Python Code)

Max Activating Token Index: 1017

Text #12

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2337. Min Act: -0.0000

Data Index: 1475981 (Python Code)

Max Activating Token Index: 978

Text #13

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2301. Min Act: -0.0000

Data Index: 1509669 (Python Code)

Max Activating Token Index: 415

Text #14

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2266. Min Act: -0.0000

Data Index: 244918 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2336. Min Act: -0.0000

Data Index: 1585402 (Python Code)

Max Activating Token Index: 471

Text #16

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2190. Min Act: -0.0000

Data Index: 1456252 (Python Code)

Max Activating Token Index: 649

Text #17

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2247. Min Act: -0.0000

Data Index: 1368707 (Python Code)

Max Activating Token Index: 881

Text #18

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2093. Min Act: -0.0000

Data Index: 1457546 (Python Code)

Max Activating Token Index: 581

Text #19

Max Range: 0.4614. Min Range: -0.4614

Max Act: 0.2300. Min Act: -0.0000

Data Index: 450220 (C4 (Web Text))

Max Activating Token Index: 382