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

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

Neuron 400 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.7232. Min Act: -0.0000

Data Index: 1551031 (Python Code)

Max Activating Token Index: 912

Text #1

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.6017. Min Act: -0.0000

Data Index: 1375593 (Python Code)

Max Activating Token Index: 383

Text #2

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.6302. Min Act: -0.0000

Data Index: 909506 (C4 (Web Text))

Max Activating Token Index: 776

Text #3

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.5164. Min Act: -0.0000

Data Index: 1385119 (Python Code)

Max Activating Token Index: 278

Text #4

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.5745. Min Act: -0.0000

Data Index: 155354 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.4978. Min Act: -0.0000

Data Index: 1616084 (Python Code)

Max Activating Token Index: 567

Text #6

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.4934. Min Act: -0.0000

Data Index: 1290961 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.5374. Min Act: -0.0000

Data Index: 1378694 (Python Code)

Max Activating Token Index: 939

Text #8

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.5355. Min Act: -0.0000

Data Index: 1566418 (Python Code)

Max Activating Token Index: 411

Text #9

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.4827. Min Act: -0.0000

Data Index: 903883 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.4389. Min Act: -0.0000

Data Index: 352474 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.4942. Min Act: -0.0000

Data Index: 8486 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.4651. Min Act: -0.0000

Data Index: 1484751 (Python Code)

Max Activating Token Index: 252

Text #13

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.4746. Min Act: -0.0000

Data Index: 1550915 (Python Code)

Max Activating Token Index: 580

Text #14

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.4511. Min Act: -0.0000

Data Index: 889642 (C4 (Web Text))

Max Activating Token Index: 443

Text #15

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.4130. Min Act: -0.0000

Data Index: 1012370 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.4401. Min Act: -0.0000

Data Index: 1552324 (Python Code)

Max Activating Token Index: 436

Text #17

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.4081. Min Act: -0.0000

Data Index: 289469 (C4 (Web Text))

Max Activating Token Index: 358

Text #18

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.4244. Min Act: -0.0000

Data Index: 1264275 (C4 (Web Text))

Max Activating Token Index: 115

Text #19

Max Range: 0.7232. Min Range: -0.7232

Max Act: 0.3934. Min Act: -0.0000

Data Index: 504552 (C4 (Web Text))

Max Activating Token Index: 211