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

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

Neuron 2653 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4082. Min Range: -5.4082

Max Act: 5.4082. Min Act: -0.0001

Data Index: 1333727 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 5.4082. Min Range: -5.4082

Max Act: 5.3550. Min Act: -0.0001

Data Index: 31396 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 5.4082. Min Range: -5.4082

Max Act: 4.0197. Min Act: -0.0001

Data Index: 490029 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 5.4082. Min Range: -5.4082

Max Act: 4.5081. Min Act: -0.0001

Data Index: 561422 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 5.4082. Min Range: -5.4082

Max Act: 4.4027. Min Act: -0.0001

Data Index: 447001 (C4 (Web Text))

Max Activating Token Index: 617

Text #5

Max Range: 5.4082. Min Range: -5.4082

Max Act: 3.6219. Min Act: -0.0001

Data Index: 1332849 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 5.4082. Min Range: -5.4082

Max Act: 4.3090. Min Act: -0.0001

Data Index: 155862 (C4 (Web Text))

Max Activating Token Index: 807

Text #7

Max Range: 5.4082. Min Range: -5.4082

Max Act: 3.8397. Min Act: -0.0001

Data Index: 840687 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 5.4082. Min Range: -5.4082

Max Act: 3.4503. Min Act: -0.0001

Data Index: 1325325 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 5.4082. Min Range: -5.4082

Max Act: 3.7132. Min Act: -0.0001

Data Index: 1147941 (C4 (Web Text))

Max Activating Token Index: 497

Text #10

Max Range: 5.4082. Min Range: -5.4082

Max Act: 3.8076. Min Act: -0.0001

Data Index: 656441 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 5.4082. Min Range: -5.4082

Max Act: 3.8441. Min Act: -0.0001

Data Index: 291319 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 5.4082. Min Range: -5.4082

Max Act: 3.5590. Min Act: -0.0001

Data Index: 1124288 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 5.4082. Min Range: -5.4082

Max Act: 3.9515. Min Act: -0.0001

Data Index: 411505 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 5.4082. Min Range: -5.4082

Max Act: 3.7680. Min Act: -0.0001

Data Index: 1197089 (C4 (Web Text))

Max Activating Token Index: 240

Text #15

Max Range: 5.4082. Min Range: -5.4082

Max Act: 3.5130. Min Act: -0.0001

Data Index: 1235060 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 5.4082. Min Range: -5.4082

Max Act: 3.1726. Min Act: -0.0001

Data Index: 1331732 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 5.4082. Min Range: -5.4082

Max Act: 3.4318. Min Act: -0.0001

Data Index: 51588 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 5.4082. Min Range: -5.4082

Max Act: 3.1445. Min Act: -0.0001

Data Index: 375190 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 5.4082. Min Range: -5.4082

Max Act: 3.2601. Min Act: -0.0001

Data Index: 294891 (C4 (Web Text))

Max Activating Token Index: 401