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

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

Neuron 3080 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.4498. Min Act: -0.0000

Data Index: 247534 (C4 (Web Text))

Max Activating Token Index: 170

Text #1

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.4014. Min Act: -0.0001

Data Index: 540101 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3740. Min Act: -0.0001

Data Index: 1316228 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3638. Min Act: -0.0001

Data Index: 850657 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3439. Min Act: -0.0000

Data Index: 688707 (C4 (Web Text))

Max Activating Token Index: 470

Text #5

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3312. Min Act: -0.0001

Data Index: 265688 (C4 (Web Text))

Max Activating Token Index: 76

Text #6

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3511. Min Act: -0.0000

Data Index: 113812 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3613. Min Act: -0.0001

Data Index: 1263120 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3472. Min Act: -0.0001

Data Index: 903108 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3477. Min Act: -0.0001

Data Index: 1354008 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3286. Min Act: -0.0001

Data Index: 1216148 (C4 (Web Text))

Max Activating Token Index: 398

Text #11

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3312. Min Act: -0.0001

Data Index: 204022 (C4 (Web Text))

Max Activating Token Index: 812

Text #12

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3409. Min Act: -0.0001

Data Index: 1076909 (C4 (Web Text))

Max Activating Token Index: 852

Text #13

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3242. Min Act: -0.0000

Data Index: 1098038 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3242. Min Act: -0.0000

Data Index: 1028583 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3210. Min Act: -0.0000

Data Index: 749662 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.2939. Min Act: -0.0001

Data Index: 780027 (C4 (Web Text))

Max Activating Token Index: 997

Text #17

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3080. Min Act: -0.0000

Data Index: 1173015 (C4 (Web Text))

Max Activating Token Index: 219

Text #18

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3046. Min Act: 0.0000

Data Index: 459251 (C4 (Web Text))

Max Activating Token Index: 643

Text #19

Max Range: 0.4498. Min Range: -0.4498

Max Act: 0.3037. Min Act: -0.0000

Data Index: 386485 (C4 (Web Text))

Max Activating Token Index: 461