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

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

Neuron 1693 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: 0.5814. Min Range: -0.5814

Max Act: 0.5814. Min Act: -0.0001

Data Index: 1032750 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.3704. Min Act: -0.0001

Data Index: 1353950 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.3541. Min Act: -0.0001

Data Index: 14758 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.3255. Min Act: -0.0001

Data Index: 1306652 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.3087. Min Act: -0.0001

Data Index: 903096 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.3024. Min Act: -0.0000

Data Index: 802250 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.2933. Min Act: -0.0001

Data Index: 167594 (C4 (Web Text))

Max Activating Token Index: 850

Text #7

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.2900. Min Act: -0.0000

Data Index: 1255102 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.2591. Min Act: -0.0001

Data Index: 1152171 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.2746. Min Act: -0.0001

Data Index: 1275038 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.2534. Min Act: -0.0000

Data Index: 1150469 (C4 (Web Text))

Max Activating Token Index: 886

Text #11

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.2467. Min Act: -0.0000

Data Index: 885132 (C4 (Web Text))

Max Activating Token Index: 26

Text #12

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.2304. Min Act: -0.0001

Data Index: 919894 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.2284. Min Act: -0.0000

Data Index: 634992 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.2310. Min Act: -0.0001

Data Index: 514014 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.2475. Min Act: -0.0000

Data Index: 107747 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.2247. Min Act: -0.0001

Data Index: 937410 (C4 (Web Text))

Max Activating Token Index: 415

Text #17

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.2314. Min Act: -0.0001

Data Index: 1284295 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.2205. Min Act: -0.0001

Data Index: 1286378 (C4 (Web Text))

Max Activating Token Index: 174

Text #19

Max Range: 0.5814. Min Range: -0.5814

Max Act: 0.2066. Min Act: -0.0001

Data Index: 524162 (C4 (Web Text))

Max Activating Token Index: 951