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

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

Neuron 2227 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.5197. Min Act: -0.0000

Data Index: 175565 (C4 (Web Text))

Max Activating Token Index: 208

Text #1

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.3704. Min Act: -0.0000

Data Index: 407436 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.2960. Min Act: -0.0000

Data Index: 375531 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.2685. Min Act: -0.0000

Data Index: 472755 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.2484. Min Act: -0.0000

Data Index: 594904 (C4 (Web Text))

Max Activating Token Index: 650

Text #5

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.2201. Min Act: -0.0000

Data Index: 260706 (C4 (Web Text))

Max Activating Token Index: 693

Text #6

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.2307. Min Act: -0.0000

Data Index: 246052 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.2217. Min Act: -0.0000

Data Index: 937082 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.2221. Min Act: -0.0000

Data Index: 457357 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.2286. Min Act: -0.0000

Data Index: 706390 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.2350. Min Act: -0.0000

Data Index: 1119805 (C4 (Web Text))

Max Activating Token Index: 1010

Text #11

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.2294. Min Act: -0.0000

Data Index: 1241565 (C4 (Web Text))

Max Activating Token Index: 841

Text #12

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.2205. Min Act: -0.0000

Data Index: 519174 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.2100. Min Act: -0.0000

Data Index: 131213 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.2068. Min Act: -0.0000

Data Index: 651074 (C4 (Web Text))

Max Activating Token Index: 50

Text #15

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.2103. Min Act: -0.0000

Data Index: 42556 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.2085. Min Act: -0.0000

Data Index: 1315282 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.2094. Min Act: -0.0000

Data Index: 139284 (C4 (Web Text))

Max Activating Token Index: 922

Text #18

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.2236. Min Act: -0.0000

Data Index: 956976 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 0.5197. Min Range: -0.5197

Max Act: 0.2079. Min Act: -0.0000

Data Index: 13363 (C4 (Web Text))

Max Activating Token Index: 817