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

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

Neuron 2741 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: 9.0723. Min Range: -9.0723

Max Act: 9.0723. Min Act: -0.0000

Data Index: 1359981 (Python Code)

Max Activating Token Index: 208

Text #1

Max Range: 9.0723. Min Range: -9.0723

Max Act: 8.4652. Min Act: -0.0000

Data Index: 1402034 (Python Code)

Max Activating Token Index: 8

Text #2

Max Range: 9.0723. Min Range: -9.0723

Max Act: 8.0981. Min Act: -0.0000

Data Index: 1556999 (Python Code)

Max Activating Token Index: 282

Text #3

Max Range: 9.0723. Min Range: -9.0723

Max Act: 7.1163. Min Act: -0.0000

Data Index: 1564823 (Python Code)

Max Activating Token Index: 31

Text #4

Max Range: 9.0723. Min Range: -9.0723

Max Act: 7.4960. Min Act: -0.0000

Data Index: 1575418 (Python Code)

Max Activating Token Index: 22

Text #5

Max Range: 9.0723. Min Range: -9.0723

Max Act: 6.8027. Min Act: -0.0000

Data Index: 1496505 (Python Code)

Max Activating Token Index: 23

Text #6

Max Range: 9.0723. Min Range: -9.0723

Max Act: 7.2291. Min Act: -0.0000

Data Index: 1483052 (Python Code)

Max Activating Token Index: 533

Text #7

Max Range: 9.0723. Min Range: -9.0723

Max Act: 7.0187. Min Act: -0.0000

Data Index: 1369705 (Python Code)

Max Activating Token Index: 204

Text #8

Max Range: 9.0723. Min Range: -9.0723

Max Act: 6.0391. Min Act: -0.0000

Data Index: 1480025 (Python Code)

Max Activating Token Index: 250

Text #9

Max Range: 9.0723. Min Range: -9.0723

Max Act: 6.8086. Min Act: -0.0000

Data Index: 1363949 (Python Code)

Max Activating Token Index: 983

Text #10

Max Range: 9.0723. Min Range: -9.0723

Max Act: 6.0641. Min Act: -0.0000

Data Index: 1525333 (Python Code)

Max Activating Token Index: 443

Text #11

Max Range: 9.0723. Min Range: -9.0723

Max Act: 6.1907. Min Act: -0.0000

Data Index: 1409195 (Python Code)

Max Activating Token Index: 282

Text #12

Max Range: 9.0723. Min Range: -9.0723

Max Act: 6.2952. Min Act: -0.0000

Data Index: 1395355 (Python Code)

Max Activating Token Index: 620

Text #13

Max Range: 9.0723. Min Range: -9.0723

Max Act: 6.1189. Min Act: -0.0000

Data Index: 1428946 (Python Code)

Max Activating Token Index: 28

Text #14

Max Range: 9.0723. Min Range: -9.0723

Max Act: 6.0408. Min Act: -0.0000

Data Index: 1531717 (Python Code)

Max Activating Token Index: 749

Text #15

Max Range: 9.0723. Min Range: -9.0723

Max Act: 6.0253. Min Act: -0.0000

Data Index: 1652510 (Python Code)

Max Activating Token Index: 304

Text #16

Max Range: 9.0723. Min Range: -9.0723

Max Act: 6.3084. Min Act: -0.0000

Data Index: 1564146 (Python Code)

Max Activating Token Index: 329

Text #17

Max Range: 9.0723. Min Range: -9.0723

Max Act: 5.6306. Min Act: -0.0000

Data Index: 1435493 (Python Code)

Max Activating Token Index: 262

Text #18

Max Range: 9.0723. Min Range: -9.0723

Max Act: 5.5372. Min Act: -0.0000

Data Index: 1466008 (Python Code)

Max Activating Token Index: 93

Text #19

Max Range: 9.0723. Min Range: -9.0723

Max Act: 5.4965. Min Act: -0.0000

Data Index: 1558876 (Python Code)

Max Activating Token Index: 173