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

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

Neuron 2322 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.9261. Min Act: -0.0001

Data Index: 1561289 (Python Code)

Max Activating Token Index: 11

Text #1

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.7747. Min Act: -0.0001

Data Index: 1596143 (Python Code)

Max Activating Token Index: 32

Text #2

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.7900. Min Act: -0.0001

Data Index: 1497596 (Python Code)

Max Activating Token Index: 318

Text #3

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.7042. Min Act: -0.0001

Data Index: 1474711 (Python Code)

Max Activating Token Index: 65

Text #4

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.6933. Min Act: -0.0000

Data Index: 1602152 (Python Code)

Max Activating Token Index: 338

Text #5

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.4618. Min Act: -0.0001

Data Index: 1544435 (Python Code)

Max Activating Token Index: 115

Text #6

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.5427. Min Act: -0.0001

Data Index: 1459961 (Python Code)

Max Activating Token Index: 100

Text #7

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.4255. Min Act: -0.0001

Data Index: 1455781 (Python Code)

Max Activating Token Index: 495

Text #8

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.5489. Min Act: -0.0001

Data Index: 1537508 (Python Code)

Max Activating Token Index: 423

Text #9

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.4699. Min Act: -0.0001

Data Index: 1546608 (Python Code)

Max Activating Token Index: 691

Text #10

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.4548. Min Act: -0.0001

Data Index: 1583070 (Python Code)

Max Activating Token Index: 581

Text #11

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.4341. Min Act: -0.0001

Data Index: 1490342 (Python Code)

Max Activating Token Index: 13

Text #12

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.3562. Min Act: -0.0001

Data Index: 1465558 (Python Code)

Max Activating Token Index: 228

Text #13

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.0892. Min Act: -0.0001

Data Index: 1391185 (Python Code)

Max Activating Token Index: 551

Text #14

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.3501. Min Act: -0.0001

Data Index: 1388293 (Python Code)

Max Activating Token Index: 18

Text #15

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.2667. Min Act: -0.0001

Data Index: 1639303 (Python Code)

Max Activating Token Index: 261

Text #16

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.4522. Min Act: -0.0001

Data Index: 1593588 (Python Code)

Max Activating Token Index: 65

Text #17

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.3998. Min Act: -0.0001

Data Index: 1606925 (Python Code)

Max Activating Token Index: 494

Text #18

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.3123. Min Act: -0.0001

Data Index: 1544804 (Python Code)

Max Activating Token Index: 373

Text #19

Max Range: 1.9261. Min Range: -1.9261

Max Act: 1.1602. Min Act: -0.0001

Data Index: 1590673 (Python Code)

Max Activating Token Index: 923