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

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

Neuron 3592 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3993. Min Range: -1.3993

Max Act: 1.3553. Min Act: -0.0000

Data Index: 1434667 (Python Code)

Max Activating Token Index: 297

Text #1

Max Range: 1.3993. Min Range: -1.3993

Max Act: 1.3593. Min Act: -0.0000

Data Index: 1401294 (Python Code)

Max Activating Token Index: 665

Text #2

Max Range: 1.3993. Min Range: -1.3993

Max Act: 1.3259. Min Act: -0.0000

Data Index: 1457196 (Python Code)

Max Activating Token Index: 977

Text #3

Max Range: 1.3993. Min Range: -1.3993

Max Act: 1.3993. Min Act: -0.0000

Data Index: 1555068 (Python Code)

Max Activating Token Index: 226

Text #4

Max Range: 1.3993. Min Range: -1.3993

Max Act: 1.3215. Min Act: -0.0000

Data Index: 1527035 (Python Code)

Max Activating Token Index: 147

Text #5

Max Range: 1.3993. Min Range: -1.3993

Max Act: 1.3225. Min Act: -0.0000

Data Index: 1402690 (Python Code)

Max Activating Token Index: 561

Text #6

Max Range: 1.3993. Min Range: -1.3993

Max Act: 1.3969. Min Act: -0.0000

Data Index: 1607111 (Python Code)

Max Activating Token Index: 93

Text #7

Max Range: 1.3993. Min Range: -1.3993

Max Act: 1.3485. Min Act: -0.0000

Data Index: 1589714 (Python Code)

Max Activating Token Index: 504

Text #8

Max Range: 1.3993. Min Range: -1.3993

Max Act: 1.3359. Min Act: -0.0000

Data Index: 1419963 (Python Code)

Max Activating Token Index: 974

Text #9

Max Range: 1.3993. Min Range: -1.3993

Max Act: 1.2898. Min Act: -0.0000

Data Index: 1361578 (Python Code)

Max Activating Token Index: 59

Text #10

Max Range: 1.3993. Min Range: -1.3993

Max Act: 1.3625. Min Act: -0.0000

Data Index: 1566893 (Python Code)

Max Activating Token Index: 1016

Text #11

Max Range: 1.3993. Min Range: -1.3993

Max Act: 1.3145. Min Act: -0.0000

Data Index: 1549353 (Python Code)

Max Activating Token Index: 449

Text #12

Max Range: 1.3993. Min Range: -1.3993

Max Act: 1.2644. Min Act: -0.0000

Data Index: 1490712 (Python Code)

Max Activating Token Index: 145

Text #13

Max Range: 1.3993. Min Range: -1.3993

Max Act: 1.2272. Min Act: -0.0000

Data Index: 1384914 (Python Code)

Max Activating Token Index: 942

Text #14

Max Range: 1.3993. Min Range: -1.3993

Max Act: 1.3001. Min Act: -0.0000

Data Index: 1485138 (Python Code)

Max Activating Token Index: 901

Text #15

Max Range: 1.3993. Min Range: -1.3993

Max Act: 1.2903. Min Act: -0.0000

Data Index: 1413502 (Python Code)

Max Activating Token Index: 700

Text #16

Max Range: 1.3993. Min Range: -1.3993

Max Act: 1.3203. Min Act: -0.0000

Data Index: 1612639 (Python Code)

Max Activating Token Index: 243

Text #17

Max Range: 1.3993. Min Range: -1.3993

Max Act: 1.3137. Min Act: -0.0000

Data Index: 1544818 (Python Code)

Max Activating Token Index: 265

Text #18

Max Range: 1.3993. Min Range: -1.3993

Max Act: 1.2651. Min Act: -0.0000

Data Index: 1527736 (Python Code)

Max Activating Token Index: 666

Text #19

Max Range: 1.3993. Min Range: -1.3993

Max Act: 1.1922. Min Act: -0.0000

Data Index: 1379572 (Python Code)

Max Activating Token Index: 226