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

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

Neuron 1294 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.9174. Min Act: -0.0000

Data Index: 1539895 (Python Code)

Max Activating Token Index: 717

Text #1

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.8376. Min Act: -0.0000

Data Index: 445996 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.7233. Min Act: -0.0000

Data Index: 116114 (C4 (Web Text))

Max Activating Token Index: 263

Text #3

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.7042. Min Act: -0.0000

Data Index: 1187227 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.6872. Min Act: -0.0000

Data Index: 1570 (C4 (Web Text))

Max Activating Token Index: 477

Text #5

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.7025. Min Act: -0.0000

Data Index: 1213428 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.6485. Min Act: -0.0000

Data Index: 303862 (C4 (Web Text))

Max Activating Token Index: 676

Text #7

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.6285. Min Act: -0.0000

Data Index: 344285 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.6448. Min Act: -0.0000

Data Index: 1144295 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.5906. Min Act: -0.0000

Data Index: 717731 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.6377. Min Act: -0.0000

Data Index: 128646 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.5929. Min Act: -0.0000

Data Index: 1042180 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.5890. Min Act: -0.0000

Data Index: 1569333 (Python Code)

Max Activating Token Index: 966

Text #13

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.5819. Min Act: -0.0000

Data Index: 308067 (C4 (Web Text))

Max Activating Token Index: 611

Text #14

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.5840. Min Act: -0.0000

Data Index: 1266004 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.5895. Min Act: -0.0000

Data Index: 532207 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.5865. Min Act: -0.0000

Data Index: 1308022 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.5532. Min Act: -0.0000

Data Index: 375701 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.5501. Min Act: -0.0000

Data Index: 596517 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 0.9174. Min Range: -0.9174

Max Act: 0.5777. Min Act: -0.0000

Data Index: 1083133 (C4 (Web Text))

Max Activating Token Index: 282