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

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

Neuron 5276 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.3070. Min Act: -0.0001

Data Index: 1625774 (Python Code)

Max Activating Token Index: 966

Text #1

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.4748. Min Act: -0.0001

Data Index: 1626992 (Python Code)

Max Activating Token Index: 902

Text #2

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.0864. Min Act: -0.0001

Data Index: 1597791 (Python Code)

Max Activating Token Index: 737

Text #3

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.1336. Min Act: -0.0001

Data Index: 1534614 (Python Code)

Max Activating Token Index: 192

Text #4

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.0730. Min Act: -0.0001

Data Index: 1565408 (Python Code)

Max Activating Token Index: 236

Text #5

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.0278. Min Act: -0.0001

Data Index: 1597023 (Python Code)

Max Activating Token Index: 87

Text #6

Max Range: 1.4748. Min Range: -1.4748

Max Act: 0.9750. Min Act: -0.0001

Data Index: 1482850 (Python Code)

Max Activating Token Index: 776

Text #7

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.1255. Min Act: -0.0001

Data Index: 1492736 (Python Code)

Max Activating Token Index: 239

Text #8

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.0208. Min Act: -0.0001

Data Index: 1371008 (Python Code)

Max Activating Token Index: 165

Text #9

Max Range: 1.4748. Min Range: -1.4748

Max Act: 0.9616. Min Act: -0.0001

Data Index: 1568147 (Python Code)

Max Activating Token Index: 442

Text #10

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.0951. Min Act: -0.0001

Data Index: 1444232 (Python Code)

Max Activating Token Index: 807

Text #11

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.1025. Min Act: -0.0001

Data Index: 1495928 (Python Code)

Max Activating Token Index: 931

Text #12

Max Range: 1.4748. Min Range: -1.4748

Max Act: 0.9004. Min Act: -0.0001

Data Index: 1473361 (Python Code)

Max Activating Token Index: 856

Text #13

Max Range: 1.4748. Min Range: -1.4748

Max Act: 0.9747. Min Act: -0.0001

Data Index: 1022440 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 1.4748. Min Range: -1.4748

Max Act: 0.9819. Min Act: -0.0001

Data Index: 1460070 (Python Code)

Max Activating Token Index: 130

Text #15

Max Range: 1.4748. Min Range: -1.4748

Max Act: 0.9234. Min Act: -0.0001

Data Index: 1434169 (Python Code)

Max Activating Token Index: 95

Text #16

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.1163. Min Act: -0.0001

Data Index: 1415497 (Python Code)

Max Activating Token Index: 347

Text #17

Max Range: 1.4748. Min Range: -1.4748

Max Act: 1.0264. Min Act: -0.0001

Data Index: 1558216 (Python Code)

Max Activating Token Index: 169

Text #18

Max Range: 1.4748. Min Range: -1.4748

Max Act: 0.9997. Min Act: -0.0001

Data Index: 1505452 (Python Code)

Max Activating Token Index: 920

Text #19

Max Range: 1.4748. Min Range: -1.4748

Max Act: 0.8153. Min Act: -0.0001

Data Index: 1495716 (Python Code)

Max Activating Token Index: 389