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

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

Neuron 2792 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5780. Min Range: -1.5780

Max Act: 1.5780. Min Act: -0.0001

Data Index: 1278418 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 1.5780. Min Range: -1.5780

Max Act: 1.3794. Min Act: -0.0002

Data Index: 971529 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 1.5780. Min Range: -1.5780

Max Act: 1.2054. Min Act: -0.0001

Data Index: 968587 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 1.5780. Min Range: -1.5780

Max Act: 1.2116. Min Act: -0.0002

Data Index: 686066 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 1.5780. Min Range: -1.5780

Max Act: 1.2761. Min Act: -0.0001

Data Index: 296599 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 1.5780. Min Range: -1.5780

Max Act: 1.2380. Min Act: -0.0001

Data Index: 1521665 (Python Code)

Max Activating Token Index: 72

Text #6

Max Range: 1.5780. Min Range: -1.5780

Max Act: 1.1981. Min Act: -0.0001

Data Index: 684401 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 1.5780. Min Range: -1.5780

Max Act: 1.2204. Min Act: -0.0001

Data Index: 922184 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 1.5780. Min Range: -1.5780

Max Act: 1.1504. Min Act: -0.0001

Data Index: 332319 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 1.5780. Min Range: -1.5780

Max Act: 1.2489. Min Act: -0.0001

Data Index: 1558169 (Python Code)

Max Activating Token Index: 612

Text #10

Max Range: 1.5780. Min Range: -1.5780

Max Act: 1.2038. Min Act: -0.0002

Data Index: 1284979 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 1.5780. Min Range: -1.5780

Max Act: 1.1974. Min Act: -0.0001

Data Index: 984016 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 1.5780. Min Range: -1.5780

Max Act: 1.2297. Min Act: -0.0001

Data Index: 707034 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 1.5780. Min Range: -1.5780

Max Act: 1.2020. Min Act: -0.0001

Data Index: 1072713 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 1.5780. Min Range: -1.5780

Max Act: 1.1603. Min Act: -0.0001

Data Index: 1324357 (C4 (Web Text))

Max Activating Token Index: 191

Text #15

Max Range: 1.5780. Min Range: -1.5780

Max Act: 1.1842. Min Act: -0.0001

Data Index: 1102940 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 1.5780. Min Range: -1.5780

Max Act: 1.2201. Min Act: -0.0001

Data Index: 31172 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 1.5780. Min Range: -1.5780

Max Act: 1.1238. Min Act: -0.0002

Data Index: 1099283 (C4 (Web Text))

Max Activating Token Index: 349

Text #18

Max Range: 1.5780. Min Range: -1.5780

Max Act: 1.1833. Min Act: -0.0001

Data Index: 383938 (C4 (Web Text))

Max Activating Token Index: 450

Text #19

Max Range: 1.5780. Min Range: -1.5780

Max Act: 1.2092. Min Act: -0.0002

Data Index: 188050 (C4 (Web Text))

Max Activating Token Index: 743