Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4518 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.3107. Min Act: -0.0000

Data Index: 1337537 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.3191. Min Act: -0.0000

Data Index: 192914 (C4 (Web Text))

Max Activating Token Index: 739

Text #2

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2931. Min Act: -0.0000

Data Index: 685756 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.3003. Min Act: -0.0000

Data Index: 326745 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2884. Min Act: -0.0000

Data Index: 892203 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.3057. Min Act: -0.0000

Data Index: 49432 (C4 (Web Text))

Max Activating Token Index: 430

Text #6

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2450. Min Act: -0.0000

Data Index: 13883 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2468. Min Act: -0.0000

Data Index: 1582046 (Python Code)

Max Activating Token Index: 1022

Text #8

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2488. Min Act: -0.0000

Data Index: 809637 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2468. Min Act: -0.0000

Data Index: 1086223 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2464. Min Act: -0.0000

Data Index: 910641 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2430. Min Act: -0.0000

Data Index: 148548 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2105. Min Act: -0.0000

Data Index: 207324 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2331. Min Act: -0.0000

Data Index: 1391460 (Python Code)

Max Activating Token Index: 770

Text #14

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2152. Min Act: -0.0000

Data Index: 313598 (C4 (Web Text))

Max Activating Token Index: 919

Text #15

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2588. Min Act: -0.0000

Data Index: 133642 (C4 (Web Text))

Max Activating Token Index: 748

Text #16

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2290. Min Act: -0.0000

Data Index: 338060 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2208. Min Act: -0.0000

Data Index: 1101404 (C4 (Web Text))

Max Activating Token Index: 798

Text #18

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2275. Min Act: -0.0000

Data Index: 301172 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 0.3191. Min Range: -0.3191

Max Act: 0.2317. Min Act: -0.0000

Data Index: 43118 (C4 (Web Text))

Max Activating Token Index: 1020