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

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

Neuron 928 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1395. Min Act: -0.0001

Data Index: 167741 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1156. Min Act: -0.0001

Data Index: 1133548 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1160. Min Act: -0.0001

Data Index: 859117 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1059. Min Act: -0.0001

Data Index: 1129613 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0991. Min Act: -0.0001

Data Index: 1007970 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0922. Min Act: -0.0001

Data Index: 361782 (C4 (Web Text))

Max Activating Token Index: 475

Text #6

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0997. Min Act: -0.0001

Data Index: 491668 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0826. Min Act: -0.0001

Data Index: 286796 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0958. Min Act: -0.0001

Data Index: 1297329 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0964. Min Act: -0.0001

Data Index: 43647 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1000. Min Act: -0.0001

Data Index: 588785 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0935. Min Act: -0.0001

Data Index: 524076 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0923. Min Act: -0.0001

Data Index: 1085031 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0888. Min Act: -0.0001

Data Index: 81344 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0906. Min Act: -0.0001

Data Index: 79887 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0947. Min Act: -0.0001

Data Index: 218895 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0913. Min Act: -0.0001

Data Index: 1075166 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0922. Min Act: -0.0001

Data Index: 272630 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0833. Min Act: -0.0001

Data Index: 485724 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0897. Min Act: -0.0002

Data Index: 10260 (C4 (Web Text))

Max Activating Token Index: 451