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

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

Neuron 4548 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5350. Min Range: -1.5350

Max Act: 1.5178. Min Act: -0.0001

Data Index: 1358468 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 1.5350. Min Range: -1.5350

Max Act: 1.4930. Min Act: -0.0001

Data Index: 22292 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 1.5350. Min Range: -1.5350

Max Act: 1.5350. Min Act: -0.0001

Data Index: 574807 (C4 (Web Text))

Max Activating Token Index: 546

Text #3

Max Range: 1.5350. Min Range: -1.5350

Max Act: 1.3790. Min Act: -0.0001

Data Index: 644039 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 1.5350. Min Range: -1.5350

Max Act: 1.3884. Min Act: -0.0001

Data Index: 664596 (C4 (Web Text))

Max Activating Token Index: 341

Text #5

Max Range: 1.5350. Min Range: -1.5350

Max Act: 1.4382. Min Act: -0.0001

Data Index: 116414 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 1.5350. Min Range: -1.5350

Max Act: 1.4291. Min Act: -0.0001

Data Index: 1220495 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 1.5350. Min Range: -1.5350

Max Act: 1.3546. Min Act: -0.0001

Data Index: 786467 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 1.5350. Min Range: -1.5350

Max Act: 1.2328. Min Act: -0.0001

Data Index: 893680 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 1.5350. Min Range: -1.5350

Max Act: 1.2595. Min Act: -0.0001

Data Index: 1134884 (C4 (Web Text))

Max Activating Token Index: 202

Text #10

Max Range: 1.5350. Min Range: -1.5350

Max Act: 1.1388. Min Act: -0.0001

Data Index: 153638 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 1.5350. Min Range: -1.5350

Max Act: 1.1873. Min Act: -0.0001

Data Index: 950582 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 1.5350. Min Range: -1.5350

Max Act: 1.1727. Min Act: -0.0001

Data Index: 584102 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 1.5350. Min Range: -1.5350

Max Act: 1.2158. Min Act: -0.0001

Data Index: 525858 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 1.5350. Min Range: -1.5350

Max Act: 1.1690. Min Act: -0.0001

Data Index: 879651 (C4 (Web Text))

Max Activating Token Index: 161

Text #15

Max Range: 1.5350. Min Range: -1.5350

Max Act: 1.1098. Min Act: -0.0001

Data Index: 705554 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 1.5350. Min Range: -1.5350

Max Act: 1.1920. Min Act: -0.0001

Data Index: 1106229 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 1.5350. Min Range: -1.5350

Max Act: 1.1526. Min Act: -0.0001

Data Index: 401747 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 1.5350. Min Range: -1.5350

Max Act: 1.2527. Min Act: -0.0001

Data Index: 1126843 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 1.5350. Min Range: -1.5350

Max Act: 1.1973. Min Act: -0.0001

Data Index: 1163537 (C4 (Web Text))

Max Activating Token Index: 172