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

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

Neuron 2212 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1465. Min Act: -0.0001

Data Index: 763590 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1238. Min Act: -0.0001

Data Index: 811934 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1362. Min Act: -0.0001

Data Index: 627177 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1174. Min Act: -0.0001

Data Index: 1274543 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1414. Min Act: -0.0001

Data Index: 904935 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1143. Min Act: -0.0001

Data Index: 564583 (C4 (Web Text))

Max Activating Token Index: 917

Text #6

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1202. Min Act: -0.0001

Data Index: 534375 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1061. Min Act: -0.0001

Data Index: 1176789 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1004. Min Act: -0.0001

Data Index: 458891 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1038. Min Act: -0.0001

Data Index: 770542 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1105. Min Act: -0.0001

Data Index: 500615 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.1186. Min Act: -0.0001

Data Index: 272117 (C4 (Web Text))

Max Activating Token Index: 597

Text #12

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.0970. Min Act: -0.0001

Data Index: 1026811 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.0995. Min Act: -0.0001

Data Index: 478667 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.0917. Min Act: -0.0001

Data Index: 641250 (C4 (Web Text))

Max Activating Token Index: 361

Text #15

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.0871. Min Act: -0.0001

Data Index: 268302 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.0934. Min Act: -0.0001

Data Index: 242342 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.0881. Min Act: -0.0001

Data Index: 129607 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.0908. Min Act: -0.0001

Data Index: 1356992 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 0.1465. Min Range: -0.1465

Max Act: 0.0875. Min Act: -0.0001

Data Index: 864206 (C4 (Web Text))

Max Activating Token Index: 1008