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

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

Neuron 3593 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: 1.9147. Min Range: -1.9147

Max Act: 1.9147. Min Act: -0.0001

Data Index: 367281 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 1.9147. Min Range: -1.9147

Max Act: 1.5259. Min Act: -0.0001

Data Index: 1073864 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 1.9147. Min Range: -1.9147

Max Act: 1.4943. Min Act: -0.0001

Data Index: 487653 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 1.9147. Min Range: -1.9147

Max Act: 1.3728. Min Act: -0.0001

Data Index: 334464 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 1.9147. Min Range: -1.9147

Max Act: 1.3559. Min Act: -0.0001

Data Index: 837183 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 1.9147. Min Range: -1.9147

Max Act: 1.4234. Min Act: -0.0001

Data Index: 322461 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 1.9147. Min Range: -1.9147

Max Act: 1.4038. Min Act: -0.0001

Data Index: 338415 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 1.9147. Min Range: -1.9147

Max Act: 1.3733. Min Act: -0.0001

Data Index: 833098 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 1.9147. Min Range: -1.9147

Max Act: 1.4039. Min Act: -0.0001

Data Index: 485936 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 1.9147. Min Range: -1.9147

Max Act: 0.9817. Min Act: -0.0001

Data Index: 656452 (C4 (Web Text))

Max Activating Token Index: 865

Text #10

Max Range: 1.9147. Min Range: -1.9147

Max Act: 1.4320. Min Act: -0.0001

Data Index: 1356992 (C4 (Web Text))

Max Activating Token Index: 659

Text #11

Max Range: 1.9147. Min Range: -1.9147

Max Act: 1.2311. Min Act: -0.0001

Data Index: 473037 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 1.9147. Min Range: -1.9147

Max Act: 1.2212. Min Act: -0.0001

Data Index: 609470 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 1.9147. Min Range: -1.9147

Max Act: 1.1938. Min Act: -0.0001

Data Index: 669998 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 1.9147. Min Range: -1.9147

Max Act: 1.2276. Min Act: -0.0001

Data Index: 833752 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 1.9147. Min Range: -1.9147

Max Act: 1.2700. Min Act: -0.0000

Data Index: 59485 (C4 (Web Text))

Max Activating Token Index: 320

Text #16

Max Range: 1.9147. Min Range: -1.9147

Max Act: 1.1886. Min Act: -0.0001

Data Index: 218253 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 1.9147. Min Range: -1.9147

Max Act: 1.2062. Min Act: -0.0001

Data Index: 935864 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 1.9147. Min Range: -1.9147

Max Act: 1.1451. Min Act: -0.0001

Data Index: 1121991 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 1.9147. Min Range: -1.9147

Max Act: 1.2011. Min Act: -0.0001

Data Index: 321404 (C4 (Web Text))

Max Activating Token Index: 383