Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2952 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0435. Min Act: -0.0003

Data Index: 974877 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0392. Min Act: -0.0002

Data Index: 714981 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0346. Min Act: -0.0003

Data Index: 1311277 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0388. Min Act: -0.0003

Data Index: 281394 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0366. Min Act: -0.0003

Data Index: 508411 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0370. Min Act: -0.0003

Data Index: 60226 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0370. Min Act: -0.0003

Data Index: 906998 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0353. Min Act: -0.0003

Data Index: 493096 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0344. Min Act: -0.0002

Data Index: 964949 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0357. Min Act: -0.0003

Data Index: 555574 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0332. Min Act: -0.0003

Data Index: 1104153 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0333. Min Act: -0.0002

Data Index: 1256398 (C4 (Web Text))

Max Activating Token Index: 255

Text #12

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1118061 (C4 (Web Text))

Max Activating Token Index: 84

Text #13

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0342. Min Act: -0.0002

Data Index: 187184 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0346. Min Act: -0.0003

Data Index: 641409 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1000204 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0349. Min Act: -0.0003

Data Index: 126251 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0343. Min Act: -0.0003

Data Index: 870966 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0335. Min Act: -0.0003

Data Index: 803591 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0332. Min Act: -0.0003

Data Index: 273436 (C4 (Web Text))

Max Activating Token Index: 31