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

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

Neuron 2204 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1483. Min Range: -3.1483

Max Act: 3.1483. Min Act: -0.0001

Data Index: 388233 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 3.1483. Min Range: -3.1483

Max Act: 2.9346. Min Act: -0.0001

Data Index: 703681 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 3.1483. Min Range: -3.1483

Max Act: 2.8259. Min Act: -0.0001

Data Index: 872851 (C4 (Web Text))

Max Activating Token Index: 295

Text #3

Max Range: 3.1483. Min Range: -3.1483

Max Act: 2.5471. Min Act: -0.0001

Data Index: 1157155 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 3.1483. Min Range: -3.1483

Max Act: 2.6501. Min Act: -0.0001

Data Index: 430754 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 3.1483. Min Range: -3.1483

Max Act: 2.2818. Min Act: -0.0001

Data Index: 1301941 (C4 (Web Text))

Max Activating Token Index: 326

Text #6

Max Range: 3.1483. Min Range: -3.1483

Max Act: 2.2571. Min Act: -0.0001

Data Index: 1153610 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 3.1483. Min Range: -3.1483

Max Act: 2.1075. Min Act: -0.0001

Data Index: 174501 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 3.1483. Min Range: -3.1483

Max Act: 2.0774. Min Act: -0.0001

Data Index: 394535 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 3.1483. Min Range: -3.1483

Max Act: 2.0474. Min Act: -0.0001

Data Index: 1077163 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 3.1483. Min Range: -3.1483

Max Act: 2.0552. Min Act: -0.0001

Data Index: 855430 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 3.1483. Min Range: -3.1483

Max Act: 2.0123. Min Act: -0.0001

Data Index: 1011843 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 3.1483. Min Range: -3.1483

Max Act: 1.7603. Min Act: -0.0001

Data Index: 882706 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 3.1483. Min Range: -3.1483

Max Act: 1.8412. Min Act: -0.0001

Data Index: 966987 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 3.1483. Min Range: -3.1483

Max Act: 1.8992. Min Act: -0.0001

Data Index: 1334968 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 3.1483. Min Range: -3.1483

Max Act: 1.9011. Min Act: -0.0001

Data Index: 45577 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 3.1483. Min Range: -3.1483

Max Act: 1.8237. Min Act: -0.0001

Data Index: 752196 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 3.1483. Min Range: -3.1483

Max Act: 1.8106. Min Act: -0.0001

Data Index: 333529 (C4 (Web Text))

Max Activating Token Index: 934

Text #18

Max Range: 3.1483. Min Range: -3.1483

Max Act: 1.8134. Min Act: -0.0001

Data Index: 793209 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 3.1483. Min Range: -3.1483

Max Act: 1.9034. Min Act: -0.0001

Data Index: 111213 (C4 (Web Text))

Max Activating Token Index: 964