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

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

Neuron 4664 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0325. Min Act: -0.0001

Data Index: 1124292 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0312. Min Act: -0.0001

Data Index: 765568 (C4 (Web Text))

Max Activating Token Index: 637

Text #2

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0314. Min Act: -0.0001

Data Index: 640907 (C4 (Web Text))

Max Activating Token Index: 776

Text #3

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0300. Min Act: -0.0001

Data Index: 1325142 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0300. Min Act: -0.0001

Data Index: 480738 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0298. Min Act: -0.0002

Data Index: 1105290 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0294. Min Act: -0.0002

Data Index: 682557 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0288. Min Act: -0.0001

Data Index: 26393 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0296. Min Act: -0.0001

Data Index: 17789 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0292. Min Act: -0.0001

Data Index: 1033682 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0292. Min Act: -0.0001

Data Index: 717766 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0288. Min Act: -0.0001

Data Index: 1345538 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0283. Min Act: -0.0001

Data Index: 287416 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0276. Min Act: -0.0001

Data Index: 749279 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0275. Min Act: -0.0001

Data Index: 569039 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0283. Min Act: -0.0002

Data Index: 220656 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0272. Min Act: -0.0001

Data Index: 1108339 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0274. Min Act: -0.0001

Data Index: 329549 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0277. Min Act: -0.0001

Data Index: 639903 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0272. Min Act: -0.0001

Data Index: 252095 (C4 (Web Text))

Max Activating Token Index: 429