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

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

Neuron 2469 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7463. Min Range: -1.7463

Max Act: 1.6271. Min Act: -0.0001

Data Index: 887257 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 1.7463. Min Range: -1.7463

Max Act: 1.6464. Min Act: -0.0001

Data Index: 1078671 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 1.7463. Min Range: -1.7463

Max Act: 1.7463. Min Act: -0.0001

Data Index: 1548118 (Python Code)

Max Activating Token Index: 299

Text #3

Max Range: 1.7463. Min Range: -1.7463

Max Act: 1.4266. Min Act: -0.0001

Data Index: 1010682 (C4 (Web Text))

Max Activating Token Index: 354

Text #4

Max Range: 1.7463. Min Range: -1.7463

Max Act: 1.5189. Min Act: -0.0001

Data Index: 728753 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 1.7463. Min Range: -1.7463

Max Act: 1.5087. Min Act: -0.0001

Data Index: 519186 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 1.7463. Min Range: -1.7463

Max Act: 1.4681. Min Act: -0.0001

Data Index: 1636546 (Python Code)

Max Activating Token Index: 525

Text #7

Max Range: 1.7463. Min Range: -1.7463

Max Act: 1.5413. Min Act: -0.0001

Data Index: 555238 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 1.7463. Min Range: -1.7463

Max Act: 1.3428. Min Act: -0.0001

Data Index: 1397719 (Python Code)

Max Activating Token Index: 666

Text #9

Max Range: 1.7463. Min Range: -1.7463

Max Act: 1.3419. Min Act: -0.0001

Data Index: 1648772 (Python Code)

Max Activating Token Index: 392

Text #10

Max Range: 1.7463. Min Range: -1.7463

Max Act: 1.3470. Min Act: -0.0001

Data Index: 1579813 (Python Code)

Max Activating Token Index: 172

Text #11

Max Range: 1.7463. Min Range: -1.7463

Max Act: 1.2881. Min Act: -0.0001

Data Index: 671458 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 1.7463. Min Range: -1.7463

Max Act: 1.3861. Min Act: -0.0001

Data Index: 1514394 (Python Code)

Max Activating Token Index: 30

Text #13

Max Range: 1.7463. Min Range: -1.7463

Max Act: 1.2811. Min Act: -0.0001

Data Index: 1398804 (Python Code)

Max Activating Token Index: 196

Text #14

Max Range: 1.7463. Min Range: -1.7463

Max Act: 1.4118. Min Act: -0.0001

Data Index: 1584281 (Python Code)

Max Activating Token Index: 744

Text #15

Max Range: 1.7463. Min Range: -1.7463

Max Act: 1.3372. Min Act: -0.0001

Data Index: 1608199 (Python Code)

Max Activating Token Index: 747

Text #16

Max Range: 1.7463. Min Range: -1.7463

Max Act: 1.1437. Min Act: -0.0001

Data Index: 1585675 (Python Code)

Max Activating Token Index: 678

Text #17

Max Range: 1.7463. Min Range: -1.7463

Max Act: 1.3990. Min Act: -0.0001

Data Index: 65494 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 1.7463. Min Range: -1.7463

Max Act: 1.2202. Min Act: -0.0001

Data Index: 1463471 (Python Code)

Max Activating Token Index: 112

Text #19

Max Range: 1.7463. Min Range: -1.7463

Max Act: 1.3286. Min Act: -0.0001

Data Index: 1577162 (Python Code)

Max Activating Token Index: 215