Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1790 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.7097. Min Act: -0.0000

Data Index: 1250368 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.8520. Min Act: -0.0000

Data Index: 580791 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.6508. Min Act: -0.0000

Data Index: 1268765 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.5675. Min Act: -0.0000

Data Index: 963200 (C4 (Web Text))

Max Activating Token Index: 842

Text #4

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.3688. Min Act: -0.0000

Data Index: 403620 (C4 (Web Text))

Max Activating Token Index: 835

Text #5

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.5422. Min Act: -0.0000

Data Index: 1175305 (C4 (Web Text))

Max Activating Token Index: 669

Text #6

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.5812. Min Act: -0.0000

Data Index: 330646 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.4728. Min Act: -0.0000

Data Index: 1078953 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.4864. Min Act: -0.0000

Data Index: 922 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.4506. Min Act: -0.0000

Data Index: 1271260 (C4 (Web Text))

Max Activating Token Index: 37

Text #10

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.4383. Min Act: -0.0000

Data Index: 724720 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.5099. Min Act: -0.0000

Data Index: 1303637 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.4186. Min Act: -0.0000

Data Index: 167706 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.4946. Min Act: -0.0000

Data Index: 1023146 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.3962. Min Act: -0.0000

Data Index: 367286 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.3080. Min Act: -0.0000

Data Index: 133361 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.3826. Min Act: -0.0000

Data Index: 461064 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.3775. Min Act: -0.0000

Data Index: 178314 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.2956. Min Act: -0.0000

Data Index: 1293575 (C4 (Web Text))

Max Activating Token Index: 658

Text #19

Max Range: 1.8520. Min Range: -1.8520

Max Act: 1.3460. Min Act: -0.0000

Data Index: 1200034 (C4 (Web Text))

Max Activating Token Index: 666