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

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

Neuron 3381 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3062. Min Range: -1.3062

Max Act: 1.3062. Min Act: -0.0000

Data Index: 613133 (C4 (Web Text))

Max Activating Token Index: 581

Text #1

Max Range: 1.3062. Min Range: -1.3062

Max Act: 1.2230. Min Act: -0.0000

Data Index: 464193 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 1.3062. Min Range: -1.3062

Max Act: 1.1756. Min Act: -0.0000

Data Index: 898760 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 1.3062. Min Range: -1.3062

Max Act: 1.1309. Min Act: -0.0000

Data Index: 55215 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 1.3062. Min Range: -1.3062

Max Act: 1.0731. Min Act: -0.0001

Data Index: 266096 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 1.3062. Min Range: -1.3062

Max Act: 1.0306. Min Act: -0.0000

Data Index: 722291 (C4 (Web Text))

Max Activating Token Index: 846

Text #6

Max Range: 1.3062. Min Range: -1.3062

Max Act: 1.0270. Min Act: -0.0000

Data Index: 739383 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 1.3062. Min Range: -1.3062

Max Act: 0.8352. Min Act: -0.0001

Data Index: 242051 (C4 (Web Text))

Max Activating Token Index: 263

Text #8

Max Range: 1.3062. Min Range: -1.3062

Max Act: 0.9026. Min Act: -0.0000

Data Index: 606548 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 1.3062. Min Range: -1.3062

Max Act: 0.8656. Min Act: -0.0001

Data Index: 479881 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 1.3062. Min Range: -1.3062

Max Act: 0.8278. Min Act: -0.0000

Data Index: 1269439 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 1.3062. Min Range: -1.3062

Max Act: 0.8923. Min Act: -0.0001

Data Index: 1210023 (C4 (Web Text))

Max Activating Token Index: 734

Text #12

Max Range: 1.3062. Min Range: -1.3062

Max Act: 0.8357. Min Act: -0.0001

Data Index: 485149 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 1.3062. Min Range: -1.3062

Max Act: 0.7818. Min Act: -0.0001

Data Index: 80008 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 1.3062. Min Range: -1.3062

Max Act: 0.7773. Min Act: -0.0000

Data Index: 1079502 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 1.3062. Min Range: -1.3062

Max Act: 0.7761. Min Act: -0.0000

Data Index: 1292696 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 1.3062. Min Range: -1.3062

Max Act: 0.7483. Min Act: -0.0001

Data Index: 747810 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 1.3062. Min Range: -1.3062

Max Act: 0.7390. Min Act: -0.0001

Data Index: 512762 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 1.3062. Min Range: -1.3062

Max Act: 0.7419. Min Act: -0.0000

Data Index: 97965 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 1.3062. Min Range: -1.3062

Max Act: 0.7666. Min Act: -0.0000

Data Index: 1013442 (C4 (Web Text))

Max Activating Token Index: 506