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

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

Neuron 527 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.3247. Min Act: -0.0001

Data Index: 1205644 (C4 (Web Text))

Max Activating Token Index: 107

Text #1

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.3330. Min Act: -0.0001

Data Index: 1103233 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.3010. Min Act: -0.0001

Data Index: 714585 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2711. Min Act: -0.0001

Data Index: 1339471 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2727. Min Act: -0.0001

Data Index: 432129 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2536. Min Act: -0.0001

Data Index: 1250898 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2463. Min Act: -0.0001

Data Index: 616815 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2406. Min Act: -0.0001

Data Index: 892554 (C4 (Web Text))

Max Activating Token Index: 350

Text #8

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2503. Min Act: -0.0001

Data Index: 423473 (C4 (Web Text))

Max Activating Token Index: 966

Text #9

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2157. Min Act: -0.0001

Data Index: 178409 (C4 (Web Text))

Max Activating Token Index: 290

Text #10

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2230. Min Act: -0.0001

Data Index: 275254 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2212. Min Act: -0.0001

Data Index: 87787 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2281. Min Act: -0.0001

Data Index: 937939 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2221. Min Act: -0.0001

Data Index: 428778 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2048. Min Act: -0.0001

Data Index: 810781 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2379. Min Act: -0.0001

Data Index: 1463612 (Python Code)

Max Activating Token Index: 331

Text #16

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2161. Min Act: -0.0001

Data Index: 1023181 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2285. Min Act: -0.0001

Data Index: 173786 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2298. Min Act: -0.0001

Data Index: 1272105 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2216. Min Act: -0.0001

Data Index: 1351398 (C4 (Web Text))

Max Activating Token Index: 495