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

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

Neuron 1898 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: 0.6268. Min Range: -0.6268

Max Act: 0.6268. Min Act: -0.0001

Data Index: 1579355 (Python Code)

Max Activating Token Index: 877

Text #1

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4842. Min Act: -0.0001

Data Index: 1454710 (Python Code)

Max Activating Token Index: 784

Text #2

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4983. Min Act: -0.0001

Data Index: 1503938 (Python Code)

Max Activating Token Index: 134

Text #3

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4342. Min Act: -0.0001

Data Index: 1372681 (Python Code)

Max Activating Token Index: 617

Text #4

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4459. Min Act: -0.0001

Data Index: 1495836 (Python Code)

Max Activating Token Index: 184

Text #5

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4418. Min Act: -0.0001

Data Index: 1530637 (Python Code)

Max Activating Token Index: 109

Text #6

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4238. Min Act: -0.0001

Data Index: 1574977 (Python Code)

Max Activating Token Index: 524

Text #7

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4078. Min Act: -0.0001

Data Index: 1571643 (Python Code)

Max Activating Token Index: 22

Text #8

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4183. Min Act: -0.0001

Data Index: 1413611 (Python Code)

Max Activating Token Index: 212

Text #9

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4180. Min Act: -0.0001

Data Index: 1417553 (Python Code)

Max Activating Token Index: 927

Text #10

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4111. Min Act: -0.0001

Data Index: 1415124 (Python Code)

Max Activating Token Index: 591

Text #11

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4408. Min Act: -0.0001

Data Index: 1546578 (Python Code)

Max Activating Token Index: 267

Text #12

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.3752. Min Act: -0.0001

Data Index: 1582833 (Python Code)

Max Activating Token Index: 100

Text #13

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.3714. Min Act: -0.0001

Data Index: 1652530 (Python Code)

Max Activating Token Index: 662

Text #14

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.3835. Min Act: -0.0001

Data Index: 1378529 (Python Code)

Max Activating Token Index: 972

Text #15

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4074. Min Act: -0.0001

Data Index: 1603598 (Python Code)

Max Activating Token Index: 142

Text #16

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4083. Min Act: -0.0001

Data Index: 1602425 (Python Code)

Max Activating Token Index: 472

Text #17

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4095. Min Act: -0.0001

Data Index: 1641125 (Python Code)

Max Activating Token Index: 1021

Text #18

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.3810. Min Act: -0.0001

Data Index: 1555093 (Python Code)

Max Activating Token Index: 471

Text #19

Max Range: 0.6268. Min Range: -0.6268

Max Act: 0.4142. Min Act: -0.0001

Data Index: 1517134 (Python Code)

Max Activating Token Index: 389