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

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

Neuron 1233 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.7462. Min Act: -0.0001

Data Index: 1336363 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.7232. Min Act: -0.0002

Data Index: 696828 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.7058. Min Act: -0.0002

Data Index: 980204 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.7374. Min Act: -0.0002

Data Index: 675085 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.7395. Min Act: -0.0002

Data Index: 739491 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.6694. Min Act: -0.0001

Data Index: 1151554 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.6918. Min Act: -0.0002

Data Index: 917206 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.6729. Min Act: -0.0001

Data Index: 662130 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.7087. Min Act: -0.0001

Data Index: 242288 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.6903. Min Act: -0.0001

Data Index: 579382 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.6579. Min Act: -0.0002

Data Index: 586747 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.5828. Min Act: -0.0002

Data Index: 1087223 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.6623. Min Act: -0.0002

Data Index: 909691 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.6774. Min Act: -0.0002

Data Index: 600260 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.6572. Min Act: -0.0002

Data Index: 1027541 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.6293. Min Act: -0.0002

Data Index: 1321162 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.5982. Min Act: -0.0002

Data Index: 890113 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.6293. Min Act: -0.0002

Data Index: 800931 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.6426. Min Act: -0.0001

Data Index: 394747 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 0.7462. Min Range: -0.7462

Max Act: 0.6681. Min Act: -0.0002

Data Index: 441550 (C4 (Web Text))

Max Activating Token Index: 744