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

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

Neuron 1442 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: 3.0277. Min Range: -3.0277

Max Act: 2.9532. Min Act: -0.0000

Data Index: 38353 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 3.0277. Min Range: -3.0277

Max Act: 3.0277. Min Act: -0.0001

Data Index: 660836 (C4 (Web Text))

Max Activating Token Index: 626

Text #2

Max Range: 3.0277. Min Range: -3.0277

Max Act: 3.0270. Min Act: -0.0001

Data Index: 1256701 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 3.0277. Min Range: -3.0277

Max Act: 2.6820. Min Act: -0.0000

Data Index: 680651 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 3.0277. Min Range: -3.0277

Max Act: 2.5446. Min Act: -0.0000

Data Index: 785495 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 3.0277. Min Range: -3.0277

Max Act: 2.6449. Min Act: -0.0000

Data Index: 258306 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 3.0277. Min Range: -3.0277

Max Act: 2.6334. Min Act: -0.0001

Data Index: 977783 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 3.0277. Min Range: -3.0277

Max Act: 2.7525. Min Act: -0.0001

Data Index: 210613 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 3.0277. Min Range: -3.0277

Max Act: 2.5932. Min Act: -0.0000

Data Index: 613256 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 3.0277. Min Range: -3.0277

Max Act: 2.4743. Min Act: -0.0000

Data Index: 1121781 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 3.0277. Min Range: -3.0277

Max Act: 2.5781. Min Act: -0.0001

Data Index: 1016447 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 3.0277. Min Range: -3.0277

Max Act: 2.5100. Min Act: -0.0001

Data Index: 232664 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 3.0277. Min Range: -3.0277

Max Act: 2.3716. Min Act: -0.0001

Data Index: 776014 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 3.0277. Min Range: -3.0277

Max Act: 2.4576. Min Act: -0.0001

Data Index: 931303 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 3.0277. Min Range: -3.0277

Max Act: 2.3275. Min Act: -0.0001

Data Index: 1305772 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 3.0277. Min Range: -3.0277

Max Act: 2.3997. Min Act: -0.0001

Data Index: 183521 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 3.0277. Min Range: -3.0277

Max Act: 2.5169. Min Act: -0.0001

Data Index: 726403 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 3.0277. Min Range: -3.0277

Max Act: 2.3705. Min Act: -0.0000

Data Index: 825813 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 3.0277. Min Range: -3.0277

Max Act: 2.2431. Min Act: -0.0000

Data Index: 197366 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 3.0277. Min Range: -3.0277

Max Act: 2.3494. Min Act: -0.0001

Data Index: 484157 (C4 (Web Text))

Max Activating Token Index: 746