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

Dataset: The Pile

Neuron 166 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0372. Min Act: 0.0000

Data Index: 550133 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0285. Min Act: -0.0000

Data Index: 1748988 (The Pile)

Max Activating Token Index: 791

Text #2

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0271. Min Act: -0.0000

Data Index: 1076810 (The Pile)

Max Activating Token Index: 645

Text #3

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0280. Min Act: -0.0000

Data Index: 757389 (The Pile)

Max Activating Token Index: 104

Text #4

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0259. Min Act: 0.0000

Data Index: 397622 (The Pile)

Max Activating Token Index: 191

Text #5

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0255. Min Act: 0.0000

Data Index: 495912 (The Pile)

Max Activating Token Index: 28

Text #6

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0254. Min Act: -0.0000

Data Index: 1515338 (The Pile)

Max Activating Token Index: 853

Text #7

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0244. Min Act: -0.0000

Data Index: 492759 (The Pile)

Max Activating Token Index: 137

Text #8

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0253. Min Act: -0.0000

Data Index: 1956629 (The Pile)

Max Activating Token Index: 446

Text #9

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0249. Min Act: -0.0000

Data Index: 502594 (The Pile)

Max Activating Token Index: 553

Text #10

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0255. Min Act: -0.0000

Data Index: 948037 (The Pile)

Max Activating Token Index: 67

Text #11

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0245. Min Act: -0.0000

Data Index: 728516 (The Pile)

Max Activating Token Index: 535

Text #12

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0244. Min Act: -0.0000

Data Index: 266952 (The Pile)

Max Activating Token Index: 300

Text #13

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0241. Min Act: -0.0000

Data Index: 1205849 (The Pile)

Max Activating Token Index: 540

Text #14

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0238. Min Act: -0.0000

Data Index: 1913450 (The Pile)

Max Activating Token Index: 685

Text #15

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0236. Min Act: -0.0000

Data Index: 1634493 (The Pile)

Max Activating Token Index: 594

Text #16

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0236. Min Act: -0.0000

Data Index: 1336833 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0226. Min Act: -0.0000

Data Index: 1969953 (The Pile)

Max Activating Token Index: 51

Text #18

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0232. Min Act: -0.0000

Data Index: 141275 (The Pile)

Max Activating Token Index: 83

Text #19

Max Range: 0.0372. Min Range: -0.0372

Max Act: 0.0240. Min Act: -0.0000

Data Index: 644906 (The Pile)

Max Activating Token Index: 123