Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1643 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1299. Min Act: -0.0001

Data Index: 673513 (C4 (Web Text))

Max Activating Token Index: 843

Text #1

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1485. Min Act: -0.0001

Data Index: 1168897 (C4 (Web Text))

Max Activating Token Index: 253

Text #2

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1536. Min Act: -0.0001

Data Index: 836991 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1388. Min Act: -0.0001

Data Index: 427820 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1303. Min Act: -0.0001

Data Index: 15288 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1336. Min Act: -0.0001

Data Index: 781439 (C4 (Web Text))

Max Activating Token Index: 625

Text #6

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1444. Min Act: -0.0001

Data Index: 1049944 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1283. Min Act: -0.0001

Data Index: 510620 (C4 (Web Text))

Max Activating Token Index: 729

Text #8

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1080. Min Act: -0.0001

Data Index: 455372 (C4 (Web Text))

Max Activating Token Index: 445

Text #9

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1316. Min Act: -0.0001

Data Index: 104353 (C4 (Web Text))

Max Activating Token Index: 827

Text #10

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1230. Min Act: -0.0001

Data Index: 458366 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1154. Min Act: -0.0001

Data Index: 885299 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1390. Min Act: -0.0001

Data Index: 283583 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1121. Min Act: -0.0001

Data Index: 141812 (C4 (Web Text))

Max Activating Token Index: 820

Text #14

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1177. Min Act: -0.0001

Data Index: 784721 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.0938. Min Act: -0.0001

Data Index: 1128409 (C4 (Web Text))

Max Activating Token Index: 765

Text #16

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1061. Min Act: -0.0001

Data Index: 857113 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1067. Min Act: -0.0001

Data Index: 537207 (C4 (Web Text))

Max Activating Token Index: 327

Text #18

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1184. Min Act: -0.0001

Data Index: 737029 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.1536. Min Range: -0.1536

Max Act: 0.1054. Min Act: -0.0001

Data Index: 730058 (C4 (Web Text))

Max Activating Token Index: 113