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

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

Neuron 3210 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4341. Min Range: -0.4341

Max Act: 0.3995. Min Act: -0.0000

Data Index: 102959 (C4 (Web Text))

Max Activating Token Index: 695

Text #1

Max Range: 0.4341. Min Range: -0.4341

Max Act: 0.4341. Min Act: -0.0000

Data Index: 1210573 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 0.4341. Min Range: -0.4341

Max Act: 0.3320. Min Act: -0.0000

Data Index: 72404 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 0.4341. Min Range: -0.4341

Max Act: 0.3897. Min Act: -0.0000

Data Index: 502529 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 0.4341. Min Range: -0.4341

Max Act: 0.3163. Min Act: -0.0000

Data Index: 833749 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 0.4341. Min Range: -0.4341

Max Act: 0.3574. Min Act: -0.0000

Data Index: 214140 (C4 (Web Text))

Max Activating Token Index: 709

Text #6

Max Range: 0.4341. Min Range: -0.4341

Max Act: 0.2847. Min Act: -0.0000

Data Index: 169560 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 0.4341. Min Range: -0.4341

Max Act: 0.2839. Min Act: -0.0000

Data Index: 824206 (C4 (Web Text))

Max Activating Token Index: 635

Text #8

Max Range: 0.4341. Min Range: -0.4341

Max Act: 0.2866. Min Act: -0.0000

Data Index: 955656 (C4 (Web Text))

Max Activating Token Index: 424

Text #9

Max Range: 0.4341. Min Range: -0.4341

Max Act: 0.2777. Min Act: -0.0000

Data Index: 523241 (C4 (Web Text))

Max Activating Token Index: 630

Text #10

Max Range: 0.4341. Min Range: -0.4341

Max Act: 0.2690. Min Act: -0.0000

Data Index: 971316 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.4341. Min Range: -0.4341

Max Act: 0.2725. Min Act: -0.0000

Data Index: 535955 (C4 (Web Text))

Max Activating Token Index: 724

Text #12

Max Range: 0.4341. Min Range: -0.4341

Max Act: 0.2520. Min Act: -0.0000

Data Index: 573344 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 0.4341. Min Range: -0.4341

Max Act: 0.2461. Min Act: -0.0000

Data Index: 965935 (C4 (Web Text))

Max Activating Token Index: 296

Text #14

Max Range: 0.4341. Min Range: -0.4341

Max Act: 0.2422. Min Act: -0.0000

Data Index: 1206317 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 0.4341. Min Range: -0.4341

Max Act: 0.2174. Min Act: -0.0000

Data Index: 431059 (C4 (Web Text))

Max Activating Token Index: 539

Text #16

Max Range: 0.4341. Min Range: -0.4341

Max Act: 0.2127. Min Act: -0.0000

Data Index: 793231 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 0.4341. Min Range: -0.4341

Max Act: 0.2250. Min Act: -0.0000

Data Index: 283329 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 0.4341. Min Range: -0.4341

Max Act: 0.2233. Min Act: -0.0000

Data Index: 40341 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 0.4341. Min Range: -0.4341

Max Act: 0.2052. Min Act: -0.0000

Data Index: 936138 (C4 (Web Text))

Max Activating Token Index: 589