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

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

Neuron 1817 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7462. Min Range: -1.7462

Max Act: 1.7462. Min Act: -0.0001

Data Index: 974115 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 1.7462. Min Range: -1.7462

Max Act: 1.5441. Min Act: -0.0001

Data Index: 253194 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 1.7462. Min Range: -1.7462

Max Act: 1.7018. Min Act: -0.0001

Data Index: 837305 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 1.7462. Min Range: -1.7462

Max Act: 1.5311. Min Act: -0.0001

Data Index: 804073 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 1.7462. Min Range: -1.7462

Max Act: 1.4318. Min Act: -0.0001

Data Index: 125269 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 1.7462. Min Range: -1.7462

Max Act: 1.5399. Min Act: -0.0001

Data Index: 726479 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 1.7462. Min Range: -1.7462

Max Act: 1.4998. Min Act: -0.0001

Data Index: 1514923 (Python Code)

Max Activating Token Index: 318

Text #7

Max Range: 1.7462. Min Range: -1.7462

Max Act: 1.4719. Min Act: -0.0001

Data Index: 412150 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 1.7462. Min Range: -1.7462

Max Act: 1.4612. Min Act: -0.0001

Data Index: 319359 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 1.7462. Min Range: -1.7462

Max Act: 1.3822. Min Act: -0.0001

Data Index: 181916 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 1.7462. Min Range: -1.7462

Max Act: 1.6189. Min Act: -0.0001

Data Index: 1500832 (Python Code)

Max Activating Token Index: 768

Text #11

Max Range: 1.7462. Min Range: -1.7462

Max Act: 1.4943. Min Act: -0.0001

Data Index: 1284981 (C4 (Web Text))

Max Activating Token Index: 242

Text #12

Max Range: 1.7462. Min Range: -1.7462

Max Act: 1.4329. Min Act: -0.0001

Data Index: 873466 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 1.7462. Min Range: -1.7462

Max Act: 1.4542. Min Act: -0.0001

Data Index: 1439155 (Python Code)

Max Activating Token Index: 633

Text #14

Max Range: 1.7462. Min Range: -1.7462

Max Act: 1.4433. Min Act: -0.0001

Data Index: 881561 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 1.7462. Min Range: -1.7462

Max Act: 1.4371. Min Act: -0.0001

Data Index: 186477 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 1.7462. Min Range: -1.7462

Max Act: 1.3855. Min Act: -0.0001

Data Index: 109607 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 1.7462. Min Range: -1.7462

Max Act: 1.3658. Min Act: -0.0001

Data Index: 1221410 (C4 (Web Text))

Max Activating Token Index: 780

Text #18

Max Range: 1.7462. Min Range: -1.7462

Max Act: 1.2190. Min Act: -0.0001

Data Index: 1099390 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 1.7462. Min Range: -1.7462

Max Act: 1.4075. Min Act: -0.0001

Data Index: 1193445 (C4 (Web Text))

Max Activating Token Index: 904