Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 5002 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.5086. Min Act: -0.0000

Data Index: 1477623 (Python Code)

Max Activating Token Index: 323

Text #1

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.5923. Min Act: -0.0000

Data Index: 1371554 (Python Code)

Max Activating Token Index: 975

Text #2

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.5344. Min Act: -0.0000

Data Index: 1655068 (Python Code)

Max Activating Token Index: 162

Text #3

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.5590. Min Act: -0.0000

Data Index: 1389101 (Python Code)

Max Activating Token Index: 487

Text #4

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.5095. Min Act: -0.0000

Data Index: 1381588 (Python Code)

Max Activating Token Index: 512

Text #5

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.5165. Min Act: -0.0000

Data Index: 1521536 (Python Code)

Max Activating Token Index: 901

Text #6

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.4750. Min Act: -0.0000

Data Index: 1512974 (Python Code)

Max Activating Token Index: 465

Text #7

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.3653. Min Act: -0.0000

Data Index: 1589607 (Python Code)

Max Activating Token Index: 350

Text #8

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.3692. Min Act: -0.0000

Data Index: 1404340 (Python Code)

Max Activating Token Index: 727

Text #9

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.3557. Min Act: -0.0000

Data Index: 1580925 (Python Code)

Max Activating Token Index: 564

Text #10

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.3081. Min Act: -0.0000

Data Index: 1397628 (Python Code)

Max Activating Token Index: 874

Text #11

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.3587. Min Act: -0.0000

Data Index: 1655707 (Python Code)

Max Activating Token Index: 414

Text #12

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.4289. Min Act: -0.0000

Data Index: 1388685 (Python Code)

Max Activating Token Index: 617

Text #13

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.3435. Min Act: -0.0000

Data Index: 1653663 (Python Code)

Max Activating Token Index: 217

Text #14

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.2476. Min Act: -0.0000

Data Index: 1582607 (Python Code)

Max Activating Token Index: 422

Text #15

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.3505. Min Act: -0.0000

Data Index: 1453799 (Python Code)

Max Activating Token Index: 303

Text #16

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.2587. Min Act: -0.0000

Data Index: 1408186 (Python Code)

Max Activating Token Index: 940

Text #17

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.2134. Min Act: -0.0000

Data Index: 1495161 (Python Code)

Max Activating Token Index: 931

Text #18

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.2395. Min Act: -0.0000

Data Index: 1369835 (Python Code)

Max Activating Token Index: 391

Text #19

Max Range: 1.5923. Min Range: -1.5923

Max Act: 1.2440. Min Act: -0.0000

Data Index: 1504842 (Python Code)

Max Activating Token Index: 636