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

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

Neuron 5075 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1293. Min Range: -1.1293

Max Act: 1.1293. Min Act: -0.0000

Data Index: 1618455 (Python Code)

Max Activating Token Index: 844

Text #1

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.9924. Min Act: -0.0000

Data Index: 1429375 (Python Code)

Max Activating Token Index: 90

Text #2

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.9941. Min Act: -0.0000

Data Index: 1543480 (Python Code)

Max Activating Token Index: 77

Text #3

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.8978. Min Act: -0.0000

Data Index: 1601370 (Python Code)

Max Activating Token Index: 466

Text #4

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.8854. Min Act: -0.0000

Data Index: 1485879 (Python Code)

Max Activating Token Index: 671

Text #5

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.8051. Min Act: -0.0000

Data Index: 1436626 (Python Code)

Max Activating Token Index: 90

Text #6

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.8927. Min Act: -0.0000

Data Index: 1465677 (Python Code)

Max Activating Token Index: 480

Text #7

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.8087. Min Act: -0.0000

Data Index: 1419058 (Python Code)

Max Activating Token Index: 247

Text #8

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.7489. Min Act: -0.0000

Data Index: 1414068 (Python Code)

Max Activating Token Index: 665

Text #9

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.8041. Min Act: -0.0000

Data Index: 1540469 (Python Code)

Max Activating Token Index: 373

Text #10

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.7725. Min Act: -0.0000

Data Index: 1381142 (Python Code)

Max Activating Token Index: 689

Text #11

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.7873. Min Act: -0.0000

Data Index: 1514678 (Python Code)

Max Activating Token Index: 252

Text #12

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.7202. Min Act: -0.0000

Data Index: 1367807 (Python Code)

Max Activating Token Index: 374

Text #13

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.7619. Min Act: -0.0000

Data Index: 1488421 (Python Code)

Max Activating Token Index: 75

Text #14

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.7473. Min Act: -0.0000

Data Index: 1656785 (Python Code)

Max Activating Token Index: 569

Text #15

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.7560. Min Act: -0.0000

Data Index: 1372374 (Python Code)

Max Activating Token Index: 842

Text #16

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.7136. Min Act: -0.0000

Data Index: 1377555 (Python Code)

Max Activating Token Index: 712

Text #17

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.7519. Min Act: -0.0000

Data Index: 1547285 (Python Code)

Max Activating Token Index: 308

Text #18

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.7489. Min Act: -0.0000

Data Index: 1485557 (Python Code)

Max Activating Token Index: 444

Text #19

Max Range: 1.1293. Min Range: -1.1293

Max Act: 0.7201. Min Act: -0.0000

Data Index: 1391471 (Python Code)

Max Activating Token Index: 28