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

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

Neuron 3319 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3057. Min Range: -2.3057

Max Act: 2.2334. Min Act: -0.0000

Data Index: 434270 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 2.3057. Min Range: -2.3057

Max Act: 2.2085. Min Act: -0.0000

Data Index: 19313 (C4 (Web Text))

Max Activating Token Index: 596

Text #2

Max Range: 2.3057. Min Range: -2.3057

Max Act: 2.3057. Min Act: -0.0000

Data Index: 192742 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 2.3057. Min Range: -2.3057

Max Act: 2.0376. Min Act: -0.0000

Data Index: 682444 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 2.3057. Min Range: -2.3057

Max Act: 1.9503. Min Act: -0.0000

Data Index: 562816 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 2.3057. Min Range: -2.3057

Max Act: 1.7157. Min Act: -0.0000

Data Index: 165455 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 2.3057. Min Range: -2.3057

Max Act: 1.8133. Min Act: -0.0000

Data Index: 187443 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 2.3057. Min Range: -2.3057

Max Act: 1.8002. Min Act: -0.0000

Data Index: 164779 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 2.3057. Min Range: -2.3057

Max Act: 1.7649. Min Act: -0.0000

Data Index: 189540 (C4 (Web Text))

Max Activating Token Index: 237

Text #9

Max Range: 2.3057. Min Range: -2.3057

Max Act: 1.7523. Min Act: -0.0000

Data Index: 967942 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 2.3057. Min Range: -2.3057

Max Act: 1.7302. Min Act: -0.0000

Data Index: 260284 (C4 (Web Text))

Max Activating Token Index: 654

Text #11

Max Range: 2.3057. Min Range: -2.3057

Max Act: 1.7114. Min Act: -0.0000

Data Index: 868560 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 2.3057. Min Range: -2.3057

Max Act: 1.7031. Min Act: -0.0000

Data Index: 1308755 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 2.3057. Min Range: -2.3057

Max Act: 1.7026. Min Act: -0.0000

Data Index: 51622 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 2.3057. Min Range: -2.3057

Max Act: 1.7133. Min Act: -0.0000

Data Index: 106631 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 2.3057. Min Range: -2.3057

Max Act: 1.6957. Min Act: -0.0000

Data Index: 1152641 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 2.3057. Min Range: -2.3057

Max Act: 1.6951. Min Act: -0.0000

Data Index: 770279 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 2.3057. Min Range: -2.3057

Max Act: 1.7580. Min Act: -0.0000

Data Index: 280 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 2.3057. Min Range: -2.3057

Max Act: 1.6542. Min Act: -0.0000

Data Index: 1167015 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 2.3057. Min Range: -2.3057

Max Act: 1.5548. Min Act: -0.0000

Data Index: 553484 (C4 (Web Text))

Max Activating Token Index: 416