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

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

Neuron 4806 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.2131. Min Act: -0.0000

Data Index: 692663 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1808. Min Act: -0.0000

Data Index: 392782 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1494. Min Act: -0.0000

Data Index: 1230328 (C4 (Web Text))

Max Activating Token Index: 830

Text #3

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1532. Min Act: -0.0000

Data Index: 672661 (C4 (Web Text))

Max Activating Token Index: 1010

Text #4

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1385. Min Act: -0.0000

Data Index: 184798 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1509. Min Act: -0.0000

Data Index: 594787 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1447. Min Act: -0.0000

Data Index: 309398 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1340. Min Act: -0.0000

Data Index: 906010 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1414. Min Act: -0.0000

Data Index: 758500 (C4 (Web Text))

Max Activating Token Index: 550

Text #9

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1388. Min Act: -0.0000

Data Index: 536678 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1435. Min Act: -0.0000

Data Index: 793737 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1326. Min Act: -0.0000

Data Index: 1006688 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1335. Min Act: -0.0000

Data Index: 157638 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1421. Min Act: -0.0000

Data Index: 1251705 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1327. Min Act: -0.0000

Data Index: 1314278 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1328. Min Act: -0.0000

Data Index: 86336 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1348. Min Act: -0.0000

Data Index: 264750 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1271. Min Act: -0.0000

Data Index: 1139916 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1344. Min Act: -0.0000

Data Index: 579730 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1276. Min Act: -0.0000

Data Index: 540274 (C4 (Web Text))

Max Activating Token Index: 402