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

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

Neuron 4786 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: 0.9466. Min Range: -0.9466

Max Act: 0.9466. Min Act: 0.0000

Data Index: 1566665 (Python Code)

Max Activating Token Index: 412

Text #1

Max Range: 0.9466. Min Range: -0.9466

Max Act: 0.8976. Min Act: -0.0000

Data Index: 1573358 (Python Code)

Max Activating Token Index: 137

Text #2

Max Range: 0.9466. Min Range: -0.9466

Max Act: 0.8495. Min Act: -0.0000

Data Index: 1392605 (Python Code)

Max Activating Token Index: 294

Text #3

Max Range: 0.9466. Min Range: -0.9466

Max Act: 0.7965. Min Act: -0.0000

Data Index: 1364766 (Python Code)

Max Activating Token Index: 821

Text #4

Max Range: 0.9466. Min Range: -0.9466

Max Act: 0.7961. Min Act: -0.0000

Data Index: 1563650 (Python Code)

Max Activating Token Index: 695

Text #5

Max Range: 0.9466. Min Range: -0.9466

Max Act: 0.7264. Min Act: -0.0000

Data Index: 1366586 (Python Code)

Max Activating Token Index: 860

Text #6

Max Range: 0.9466. Min Range: -0.9466

Max Act: 0.7154. Min Act: -0.0000

Data Index: 1470831 (Python Code)

Max Activating Token Index: 450

Text #7

Max Range: 0.9466. Min Range: -0.9466

Max Act: 0.7418. Min Act: -0.0001

Data Index: 1581573 (Python Code)

Max Activating Token Index: 117

Text #8

Max Range: 0.9466. Min Range: -0.9466

Max Act: 0.6191. Min Act: -0.0000

Data Index: 1365772 (Python Code)

Max Activating Token Index: 104

Text #9

Max Range: 0.9466. Min Range: -0.9466

Max Act: 0.6369. Min Act: -0.0000

Data Index: 1632855 (Python Code)

Max Activating Token Index: 523

Text #10

Max Range: 0.9466. Min Range: -0.9466

Max Act: 0.6085. Min Act: -0.0000

Data Index: 1525892 (Python Code)

Max Activating Token Index: 1017

Text #11

Max Range: 0.9466. Min Range: -0.9466

Max Act: 0.6556. Min Act: -0.0000

Data Index: 1574547 (Python Code)

Max Activating Token Index: 614

Text #12

Max Range: 0.9466. Min Range: -0.9466

Max Act: 0.6054. Min Act: -0.0001

Data Index: 1371372 (Python Code)

Max Activating Token Index: 643

Text #13

Max Range: 0.9466. Min Range: -0.9466

Max Act: 0.6035. Min Act: -0.0000

Data Index: 1482484 (Python Code)

Max Activating Token Index: 396

Text #14

Max Range: 0.9466. Min Range: -0.9466

Max Act: 0.5747. Min Act: -0.0000

Data Index: 1593109 (Python Code)

Max Activating Token Index: 854

Text #15

Max Range: 0.9466. Min Range: -0.9466

Max Act: 0.5932. Min Act: -0.0000

Data Index: 1372715 (Python Code)

Max Activating Token Index: 144

Text #16

Max Range: 0.9466. Min Range: -0.9466

Max Act: 0.6320. Min Act: -0.0000

Data Index: 1444973 (Python Code)

Max Activating Token Index: 308

Text #17

Max Range: 0.9466. Min Range: -0.9466

Max Act: 0.6051. Min Act: -0.0000

Data Index: 1393504 (Python Code)

Max Activating Token Index: 356

Text #18

Max Range: 0.9466. Min Range: -0.9466

Max Act: 0.6070. Min Act: -0.0000

Data Index: 1632735 (Python Code)

Max Activating Token Index: 592

Text #19

Max Range: 0.9466. Min Range: -0.9466

Max Act: 0.6124. Min Act: -0.0000

Data Index: 1406712 (Python Code)

Max Activating Token Index: 782