Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 951 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4190. Min Act: -0.0001

Data Index: 1583694 (Python Code)

Max Activating Token Index: 642

Text #1

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4393. Min Act: -0.0001

Data Index: 1531293 (Python Code)

Max Activating Token Index: 697

Text #2

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4698. Min Act: -0.0001

Data Index: 1611785 (Python Code)

Max Activating Token Index: 621

Text #3

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4378. Min Act: -0.0001

Data Index: 1429015 (Python Code)

Max Activating Token Index: 910

Text #4

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4521. Min Act: -0.0001

Data Index: 1518381 (Python Code)

Max Activating Token Index: 457

Text #5

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4490. Min Act: -0.0001

Data Index: 1543811 (Python Code)

Max Activating Token Index: 951

Text #6

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4347. Min Act: -0.0001

Data Index: 1490076 (Python Code)

Max Activating Token Index: 289

Text #7

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4445. Min Act: -0.0001

Data Index: 1478296 (Python Code)

Max Activating Token Index: 751

Text #8

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4272. Min Act: -0.0001

Data Index: 1412974 (Python Code)

Max Activating Token Index: 210

Text #9

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4394. Min Act: -0.0001

Data Index: 1365271 (Python Code)

Max Activating Token Index: 143

Text #10

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4095. Min Act: -0.0001

Data Index: 1447023 (Python Code)

Max Activating Token Index: 861

Text #11

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4336. Min Act: -0.0001

Data Index: 1638981 (Python Code)

Max Activating Token Index: 251

Text #12

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4456. Min Act: -0.0001

Data Index: 1622868 (Python Code)

Max Activating Token Index: 859

Text #13

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4111. Min Act: -0.0001

Data Index: 1522702 (Python Code)

Max Activating Token Index: 964

Text #14

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4113. Min Act: -0.0001

Data Index: 1386304 (Python Code)

Max Activating Token Index: 279

Text #15

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4382. Min Act: -0.0001

Data Index: 1517807 (Python Code)

Max Activating Token Index: 994

Text #16

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4248. Min Act: -0.0001

Data Index: 1590206 (Python Code)

Max Activating Token Index: 884

Text #17

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3978. Min Act: -0.0001

Data Index: 1542024 (Python Code)

Max Activating Token Index: 630

Text #18

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3832. Min Act: -0.0001

Data Index: 1445760 (Python Code)

Max Activating Token Index: 294

Text #19

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3822. Min Act: -0.0001

Data Index: 1376184 (Python Code)

Max Activating Token Index: 469