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

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

Neuron 5976 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: 1.3188. Min Range: -1.3188

Max Act: 1.3188. Min Act: -0.0000

Data Index: 1100404 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 1.3188. Min Range: -1.3188

Max Act: 0.8739. Min Act: -0.0000

Data Index: 1496690 (Python Code)

Max Activating Token Index: 429

Text #2

Max Range: 1.3188. Min Range: -1.3188

Max Act: 0.9946. Min Act: -0.0000

Data Index: 1541139 (Python Code)

Max Activating Token Index: 200

Text #3

Max Range: 1.3188. Min Range: -1.3188

Max Act: 0.9191. Min Act: -0.0000

Data Index: 856506 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 1.3188. Min Range: -1.3188

Max Act: 0.9775. Min Act: -0.0000

Data Index: 1088707 (C4 (Web Text))

Max Activating Token Index: 859

Text #5

Max Range: 1.3188. Min Range: -1.3188

Max Act: 0.9169. Min Act: -0.0000

Data Index: 1461112 (Python Code)

Max Activating Token Index: 721

Text #6

Max Range: 1.3188. Min Range: -1.3188

Max Act: 0.9201. Min Act: -0.0000

Data Index: 1566227 (Python Code)

Max Activating Token Index: 672

Text #7

Max Range: 1.3188. Min Range: -1.3188

Max Act: 0.8630. Min Act: -0.0000

Data Index: 1476937 (Python Code)

Max Activating Token Index: 297

Text #8

Max Range: 1.3188. Min Range: -1.3188

Max Act: 0.8842. Min Act: -0.0000

Data Index: 1052844 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 1.3188. Min Range: -1.3188

Max Act: 0.8778. Min Act: -0.0000

Data Index: 1499218 (Python Code)

Max Activating Token Index: 319

Text #10

Max Range: 1.3188. Min Range: -1.3188

Max Act: 0.9416. Min Act: -0.0000

Data Index: 690440 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 1.3188. Min Range: -1.3188

Max Act: 0.9031. Min Act: -0.0000

Data Index: 1460361 (Python Code)

Max Activating Token Index: 303

Text #12

Max Range: 1.3188. Min Range: -1.3188

Max Act: 0.8985. Min Act: -0.0000

Data Index: 1509092 (Python Code)

Max Activating Token Index: 790

Text #13

Max Range: 1.3188. Min Range: -1.3188

Max Act: 0.8885. Min Act: -0.0000

Data Index: 1476730 (Python Code)

Max Activating Token Index: 1014

Text #14

Max Range: 1.3188. Min Range: -1.3188

Max Act: 0.8508. Min Act: -0.0000

Data Index: 1479054 (Python Code)

Max Activating Token Index: 718

Text #15

Max Range: 1.3188. Min Range: -1.3188

Max Act: 0.8914. Min Act: -0.0000

Data Index: 1421590 (Python Code)

Max Activating Token Index: 401

Text #16

Max Range: 1.3188. Min Range: -1.3188

Max Act: 0.8346. Min Act: -0.0000

Data Index: 1414630 (Python Code)

Max Activating Token Index: 630

Text #17

Max Range: 1.3188. Min Range: -1.3188

Max Act: 0.9134. Min Act: -0.0000

Data Index: 1606503 (Python Code)

Max Activating Token Index: 835

Text #18

Max Range: 1.3188. Min Range: -1.3188

Max Act: 0.8521. Min Act: -0.0000

Data Index: 1202652 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 1.3188. Min Range: -1.3188

Max Act: 0.9060. Min Act: -0.0000

Data Index: 701996 (C4 (Web Text))

Max Activating Token Index: 556