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

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

Neuron 3708 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6909. Min Act: -0.0001

Data Index: 1306115 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6953. Min Act: -0.0001

Data Index: 1069956 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6863. Min Act: -0.0001

Data Index: 687435 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6528. Min Act: -0.0001

Data Index: 53758 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6939. Min Act: -0.0001

Data Index: 528685 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6336. Min Act: -0.0001

Data Index: 570689 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6537. Min Act: -0.0001

Data Index: 596334 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6233. Min Act: -0.0000

Data Index: 1182289 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5899. Min Act: -0.0001

Data Index: 1003922 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6179. Min Act: -0.0001

Data Index: 1106784 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5969. Min Act: -0.0001

Data Index: 380670 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5990. Min Act: -0.0001

Data Index: 1113668 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6126. Min Act: -0.0001

Data Index: 553379 (C4 (Web Text))

Max Activating Token Index: 329

Text #13

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6139. Min Act: -0.0000

Data Index: 289299 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5696. Min Act: -0.0000

Data Index: 335068 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.6485. Min Act: -0.0001

Data Index: 769723 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5674. Min Act: -0.0001

Data Index: 174857 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5690. Min Act: -0.0001

Data Index: 31814 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5799. Min Act: -0.0001

Data Index: 796521 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 0.6953. Min Range: -0.6953

Max Act: 0.5482. Min Act: -0.0001

Data Index: 827073 (C4 (Web Text))

Max Activating Token Index: 474