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

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

Neuron 3870 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.8413. Min Act: -0.0001

Data Index: 247299 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.4100. Min Act: -0.0001

Data Index: 599443 (C4 (Web Text))

Max Activating Token Index: 661

Text #2

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.5686. Min Act: -0.0001

Data Index: 183010 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.5128. Min Act: -0.0001

Data Index: 356012 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.6491. Min Act: -0.0001

Data Index: 858783 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.4222. Min Act: -0.0001

Data Index: 1139380 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.4451. Min Act: -0.0001

Data Index: 1027188 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.4914. Min Act: -0.0001

Data Index: 392193 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.6278. Min Act: -0.0001

Data Index: 876161 (C4 (Web Text))

Max Activating Token Index: 566

Text #9

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.4706. Min Act: -0.0001

Data Index: 621364 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.3858. Min Act: -0.0001

Data Index: 1037089 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.3991. Min Act: -0.0001

Data Index: 909011 (C4 (Web Text))

Max Activating Token Index: 346

Text #12

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.4045. Min Act: -0.0001

Data Index: 406219 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.5166. Min Act: -0.0001

Data Index: 763203 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.4405. Min Act: -0.0001

Data Index: 207803 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.3199. Min Act: -0.0001

Data Index: 512040 (C4 (Web Text))

Max Activating Token Index: 522

Text #16

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.3141. Min Act: -0.0001

Data Index: 1130645 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.4199. Min Act: -0.0001

Data Index: 188900 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.3871. Min Act: -0.0001

Data Index: 1308997 (C4 (Web Text))

Max Activating Token Index: 186

Text #19

Max Range: 1.8413. Min Range: -1.8413

Max Act: 1.3813. Min Act: -0.0001

Data Index: 779797 (C4 (Web Text))

Max Activating Token Index: 754