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

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

Neuron 4583 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.4134. Min Act: -0.0000

Data Index: 529423 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3633. Min Act: -0.0000

Data Index: 850243 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.3068. Min Act: -0.0000

Data Index: 948873 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2789. Min Act: -0.0000

Data Index: 213881 (C4 (Web Text))

Max Activating Token Index: 16

Text #4

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2840. Min Act: -0.0000

Data Index: 1132396 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2667. Min Act: -0.0000

Data Index: 329146 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2592. Min Act: -0.0000

Data Index: 576369 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2630. Min Act: -0.0000

Data Index: 240490 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2312. Min Act: -0.0000

Data Index: 143656 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2397. Min Act: -0.0000

Data Index: 1267054 (C4 (Web Text))

Max Activating Token Index: 753

Text #10

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2198. Min Act: -0.0000

Data Index: 33382 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2165. Min Act: -0.0000

Data Index: 1006621 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2210. Min Act: -0.0000

Data Index: 14756 (C4 (Web Text))

Max Activating Token Index: 762

Text #13

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2127. Min Act: -0.0000

Data Index: 309943 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2312. Min Act: -0.0000

Data Index: 826835 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2152. Min Act: -0.0000

Data Index: 254096 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2207. Min Act: -0.0000

Data Index: 762511 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2193. Min Act: -0.0000

Data Index: 1043910 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.2063. Min Act: -0.0000

Data Index: 940160 (C4 (Web Text))

Max Activating Token Index: 816

Text #19

Max Range: 0.4134. Min Range: -0.4134

Max Act: 0.1939. Min Act: -0.0000

Data Index: 920745 (C4 (Web Text))

Max Activating Token Index: 596