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

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

Neuron 3984 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.3077. Min Act: -0.0000

Data Index: 982569 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.3146. Min Act: -0.0000

Data Index: 775684 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2986. Min Act: -0.0000

Data Index: 997212 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.3080. Min Act: -0.0000

Data Index: 1105806 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2983. Min Act: -0.0000

Data Index: 761498 (C4 (Web Text))

Max Activating Token Index: 200

Text #5

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2762. Min Act: -0.0000

Data Index: 1076012 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2537. Min Act: -0.0000

Data Index: 1265105 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2628. Min Act: -0.0000

Data Index: 1337004 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2555. Min Act: -0.0000

Data Index: 891645 (C4 (Web Text))

Max Activating Token Index: 126

Text #9

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2385. Min Act: -0.0000

Data Index: 643923 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2447. Min Act: -0.0000

Data Index: 70641 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2441. Min Act: -0.0000

Data Index: 800416 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2319. Min Act: -0.0000

Data Index: 983005 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2366. Min Act: -0.0000

Data Index: 832416 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2275. Min Act: -0.0000

Data Index: 333555 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2375. Min Act: -0.0000

Data Index: 1110836 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2358. Min Act: -0.0000

Data Index: 619867 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2231. Min Act: -0.0000

Data Index: 567635 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2107. Min Act: -0.0000

Data Index: 788331 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2120. Min Act: -0.0000

Data Index: 1164137 (C4 (Web Text))

Max Activating Token Index: 959