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

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

Neuron 1836 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.3683. Min Act: -0.0000

Data Index: 464160 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.3177. Min Act: -0.0000

Data Index: 9757 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2973. Min Act: -0.0000

Data Index: 623817 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2607. Min Act: -0.0000

Data Index: 795049 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2480. Min Act: -0.0000

Data Index: 882884 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2652. Min Act: -0.0000

Data Index: 839077 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2453. Min Act: -0.0000

Data Index: 1195033 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2616. Min Act: -0.0000

Data Index: 836946 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2504. Min Act: -0.0000

Data Index: 532924 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2487. Min Act: -0.0000

Data Index: 996347 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2393. Min Act: -0.0000

Data Index: 1264299 (C4 (Web Text))

Max Activating Token Index: 516

Text #11

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2391. Min Act: -0.0000

Data Index: 790443 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2446. Min Act: -0.0000

Data Index: 125274 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2230. Min Act: -0.0000

Data Index: 26270 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2238. Min Act: -0.0000

Data Index: 4704 (C4 (Web Text))

Max Activating Token Index: 1006

Text #15

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2311. Min Act: -0.0000

Data Index: 856194 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2288. Min Act: -0.0000

Data Index: 1139933 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2218. Min Act: -0.0000

Data Index: 674939 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2251. Min Act: -0.0000

Data Index: 459587 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.3683. Min Range: -0.3683

Max Act: 0.2242. Min Act: -0.0000

Data Index: 1255383 (C4 (Web Text))

Max Activating Token Index: 682