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

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

Neuron 1440 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5862. Min Range: -0.5862

Max Act: 0.5862. Min Act: -0.0000

Data Index: 1423517 (Python Code)

Max Activating Token Index: 842

Text #1

Max Range: 0.5862. Min Range: -0.5862

Max Act: 0.5478. Min Act: -0.0001

Data Index: 1638271 (Python Code)

Max Activating Token Index: 507

Text #2

Max Range: 0.5862. Min Range: -0.5862

Max Act: 0.5050. Min Act: 0.0001

Data Index: 1496607 (Python Code)

Max Activating Token Index: 542

Text #3

Max Range: 0.5862. Min Range: -0.5862

Max Act: 0.5001. Min Act: -0.0000

Data Index: 1647352 (Python Code)

Max Activating Token Index: 891

Text #4

Max Range: 0.5862. Min Range: -0.5862

Max Act: 0.4726. Min Act: -0.0000

Data Index: 1533754 (Python Code)

Max Activating Token Index: 667

Text #5

Max Range: 0.5862. Min Range: -0.5862

Max Act: 0.5098. Min Act: -0.0000

Data Index: 1463933 (Python Code)

Max Activating Token Index: 360

Text #6

Max Range: 0.5862. Min Range: -0.5862

Max Act: 0.4652. Min Act: -0.0000

Data Index: 1631516 (Python Code)

Max Activating Token Index: 750

Text #7

Max Range: 0.5862. Min Range: -0.5862

Max Act: 0.4277. Min Act: 0.0001

Data Index: 1481255 (Python Code)

Max Activating Token Index: 495

Text #8

Max Range: 0.5862. Min Range: -0.5862

Max Act: 0.4327. Min Act: -0.0000

Data Index: 879051 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 0.5862. Min Range: -0.5862

Max Act: 0.4297. Min Act: -0.0001

Data Index: 366528 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 0.5862. Min Range: -0.5862

Max Act: 0.4187. Min Act: -0.0000

Data Index: 1085315 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 0.5862. Min Range: -0.5862

Max Act: 0.3878. Min Act: -0.0000

Data Index: 1656298 (Python Code)

Max Activating Token Index: 876

Text #12

Max Range: 0.5862. Min Range: -0.5862

Max Act: 0.4053. Min Act: -0.0000

Data Index: 1463996 (Python Code)

Max Activating Token Index: 185

Text #13

Max Range: 0.5862. Min Range: -0.5862

Max Act: 0.4284. Min Act: 0.0000

Data Index: 1374768 (Python Code)

Max Activating Token Index: 579

Text #14

Max Range: 0.5862. Min Range: -0.5862

Max Act: 0.4117. Min Act: -0.0001

Data Index: 1598736 (Python Code)

Max Activating Token Index: 190

Text #15

Max Range: 0.5862. Min Range: -0.5862

Max Act: 0.3966. Min Act: -0.0000

Data Index: 1359282 (C4 (Web Text))

Max Activating Token Index: 144

Text #16

Max Range: 0.5862. Min Range: -0.5862

Max Act: 0.4106. Min Act: -0.0000

Data Index: 1406263 (Python Code)

Max Activating Token Index: 419

Text #17

Max Range: 0.5862. Min Range: -0.5862

Max Act: 0.3780. Min Act: -0.0000

Data Index: 1365319 (Python Code)

Max Activating Token Index: 647

Text #18

Max Range: 0.5862. Min Range: -0.5862

Max Act: 0.3823. Min Act: -0.0000

Data Index: 1607363 (Python Code)

Max Activating Token Index: 287

Text #19

Max Range: 0.5862. Min Range: -0.5862

Max Act: 0.3949. Min Act: -0.0000

Data Index: 1564999 (Python Code)

Max Activating Token Index: 876