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

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

Neuron 2881 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: 1.5455. Min Range: -1.5455

Max Act: 1.5455. Min Act: -0.0001

Data Index: 900308 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.3711. Min Act: -0.0001

Data Index: 999712 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.3203. Min Act: -0.0001

Data Index: 111480 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.2621. Min Act: -0.0001

Data Index: 934253 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.2498. Min Act: -0.0001

Data Index: 1053225 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.1477. Min Act: -0.0001

Data Index: 1097098 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.1761. Min Act: -0.0001

Data Index: 1017657 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.1792. Min Act: -0.0001

Data Index: 1097514 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.0969. Min Act: -0.0001

Data Index: 24087 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.1138. Min Act: -0.0001

Data Index: 975121 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.1841. Min Act: -0.0001

Data Index: 532462 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.0918. Min Act: -0.0001

Data Index: 1103470 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.0925. Min Act: -0.0001

Data Index: 1016732 (C4 (Web Text))

Max Activating Token Index: 117

Text #13

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.0457. Min Act: -0.0001

Data Index: 851171 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.1075. Min Act: -0.0001

Data Index: 1262030 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.0335. Min Act: -0.0001

Data Index: 308620 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.0314. Min Act: -0.0001

Data Index: 31093 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 1.5455. Min Range: -1.5455

Max Act: 0.9987. Min Act: -0.0001

Data Index: 997296 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 1.5455. Min Range: -1.5455

Max Act: 0.9714. Min Act: -0.0001

Data Index: 74199 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 1.5455. Min Range: -1.5455

Max Act: 1.0364. Min Act: -0.0001

Data Index: 1168300 (C4 (Web Text))

Max Activating Token Index: 804