Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2438 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.8080. Min Act: -0.0002

Data Index: 1925718 (The Pile)

Max Activating Token Index: 1006

Text #1

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6860. Min Act: -0.0001

Data Index: 695935 (The Pile)

Max Activating Token Index: 333

Text #2

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6510. Min Act: -0.0001

Data Index: 410554 (The Pile)

Max Activating Token Index: 279

Text #3

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6728. Min Act: -0.0001

Data Index: 1970043 (The Pile)

Max Activating Token Index: 5

Text #4

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6505. Min Act: -0.0001

Data Index: 1493431 (The Pile)

Max Activating Token Index: 190

Text #5

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6687. Min Act: -0.0001

Data Index: 1471181 (The Pile)

Max Activating Token Index: 205

Text #6

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5808. Min Act: -0.0001

Data Index: 975331 (The Pile)

Max Activating Token Index: 202

Text #7

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6383. Min Act: -0.0001

Data Index: 1114855 (The Pile)

Max Activating Token Index: 192

Text #8

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6055. Min Act: -0.0001

Data Index: 435755 (The Pile)

Max Activating Token Index: 236

Text #9

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5896. Min Act: -0.0001

Data Index: 725164 (The Pile)

Max Activating Token Index: 57

Text #10

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6262. Min Act: -0.0001

Data Index: 343269 (The Pile)

Max Activating Token Index: 463

Text #11

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6349. Min Act: -0.0001

Data Index: 1870781 (The Pile)

Max Activating Token Index: 250

Text #12

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5550. Min Act: -0.0001

Data Index: 1316404 (The Pile)

Max Activating Token Index: 58

Text #13

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6374. Min Act: -0.0001

Data Index: 21764 (The Pile)

Max Activating Token Index: 220

Text #14

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5635. Min Act: -0.0001

Data Index: 1004891 (The Pile)

Max Activating Token Index: 594

Text #15

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5697. Min Act: -0.0001

Data Index: 646656 (The Pile)

Max Activating Token Index: 527

Text #16

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5938. Min Act: -0.0001

Data Index: 777525 (The Pile)

Max Activating Token Index: 231

Text #17

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5987. Min Act: -0.0001

Data Index: 1928666 (The Pile)

Max Activating Token Index: 190

Text #18

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.6044. Min Act: -0.0001

Data Index: 1176364 (The Pile)

Max Activating Token Index: 265

Text #19

Max Range: 0.8080. Min Range: -0.8080

Max Act: 0.5810. Min Act: -0.0001

Data Index: 1611481 (The Pile)

Max Activating Token Index: 251