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

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

Neuron 4127 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2583. Min Range: -2.2583

Max Act: 2.2583. Min Act: -0.0000

Data Index: 39681 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 2.2583. Min Range: -2.2583

Max Act: 2.0936. Min Act: -0.0000

Data Index: 565615 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 2.2583. Min Range: -2.2583

Max Act: 1.8554. Min Act: -0.0000

Data Index: 686731 (C4 (Web Text))

Max Activating Token Index: 984

Text #3

Max Range: 2.2583. Min Range: -2.2583

Max Act: 1.8602. Min Act: -0.0000

Data Index: 996518 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 2.2583. Min Range: -2.2583

Max Act: 1.8356. Min Act: -0.0000

Data Index: 1098078 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 2.2583. Min Range: -2.2583

Max Act: 1.5939. Min Act: -0.0000

Data Index: 731311 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 2.2583. Min Range: -2.2583

Max Act: 1.5336. Min Act: -0.0000

Data Index: 744470 (C4 (Web Text))

Max Activating Token Index: 471

Text #7

Max Range: 2.2583. Min Range: -2.2583

Max Act: 1.4378. Min Act: -0.0000

Data Index: 57051 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 2.2583. Min Range: -2.2583

Max Act: 1.5863. Min Act: -0.0000

Data Index: 1162546 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 2.2583. Min Range: -2.2583

Max Act: 1.4734. Min Act: -0.0000

Data Index: 373224 (C4 (Web Text))

Max Activating Token Index: 931

Text #10

Max Range: 2.2583. Min Range: -2.2583

Max Act: 1.5442. Min Act: -0.0000

Data Index: 288525 (C4 (Web Text))

Max Activating Token Index: 944

Text #11

Max Range: 2.2583. Min Range: -2.2583

Max Act: 1.4431. Min Act: -0.0000

Data Index: 1024808 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 2.2583. Min Range: -2.2583

Max Act: 1.5315. Min Act: -0.0000

Data Index: 1126378 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 2.2583. Min Range: -2.2583

Max Act: 1.4227. Min Act: -0.0000

Data Index: 271863 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 2.2583. Min Range: -2.2583

Max Act: 1.4043. Min Act: -0.0000

Data Index: 1195772 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 2.2583. Min Range: -2.2583

Max Act: 1.1654. Min Act: -0.0000

Data Index: 257155 (C4 (Web Text))

Max Activating Token Index: 756

Text #16

Max Range: 2.2583. Min Range: -2.2583

Max Act: 1.2641. Min Act: -0.0000

Data Index: 781819 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 2.2583. Min Range: -2.2583

Max Act: 1.3258. Min Act: -0.0000

Data Index: 381668 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 2.2583. Min Range: -2.2583

Max Act: 1.2320. Min Act: -0.0000

Data Index: 508567 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 2.2583. Min Range: -2.2583

Max Act: 1.2177. Min Act: -0.0000

Data Index: 399885 (C4 (Web Text))

Max Activating Token Index: 713