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

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

Neuron 5459 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6088. Min Range: -0.6088

Max Act: 0.6088. Min Act: -0.0000

Data Index: 75425 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 0.6088. Min Range: -0.6088

Max Act: 0.5807. Min Act: -0.0000

Data Index: 92896 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 0.6088. Min Range: -0.6088

Max Act: 0.5773. Min Act: -0.0000

Data Index: 1261803 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 0.6088. Min Range: -0.6088

Max Act: 0.5587. Min Act: -0.0000

Data Index: 1143017 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 0.6088. Min Range: -0.6088

Max Act: 0.5035. Min Act: -0.0000

Data Index: 105418 (C4 (Web Text))

Max Activating Token Index: 353

Text #5

Max Range: 0.6088. Min Range: -0.6088

Max Act: 0.4825. Min Act: -0.0000

Data Index: 1006812 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 0.6088. Min Range: -0.6088

Max Act: 0.4805. Min Act: -0.0000

Data Index: 26524 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 0.6088. Min Range: -0.6088

Max Act: 0.4614. Min Act: -0.0000

Data Index: 901093 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 0.6088. Min Range: -0.6088

Max Act: 0.4381. Min Act: -0.0000

Data Index: 40882 (C4 (Web Text))

Max Activating Token Index: 319

Text #9

Max Range: 0.6088. Min Range: -0.6088

Max Act: 0.4681. Min Act: -0.0000

Data Index: 778778 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 0.6088. Min Range: -0.6088

Max Act: 0.4319. Min Act: -0.0000

Data Index: 283795 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 0.6088. Min Range: -0.6088

Max Act: 0.4724. Min Act: -0.0000

Data Index: 685027 (C4 (Web Text))

Max Activating Token Index: 932

Text #12

Max Range: 0.6088. Min Range: -0.6088

Max Act: 0.4326. Min Act: -0.0000

Data Index: 1343404 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 0.6088. Min Range: -0.6088

Max Act: 0.4347. Min Act: -0.0000

Data Index: 160166 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 0.6088. Min Range: -0.6088

Max Act: 0.4373. Min Act: -0.0000

Data Index: 581272 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 0.6088. Min Range: -0.6088

Max Act: 0.4369. Min Act: -0.0000

Data Index: 526642 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 0.6088. Min Range: -0.6088

Max Act: 0.4322. Min Act: -0.0000

Data Index: 205377 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 0.6088. Min Range: -0.6088

Max Act: 0.4152. Min Act: -0.0000

Data Index: 1233343 (C4 (Web Text))

Max Activating Token Index: 550

Text #18

Max Range: 0.6088. Min Range: -0.6088

Max Act: 0.4146. Min Act: -0.0000

Data Index: 1088125 (C4 (Web Text))

Max Activating Token Index: 521

Text #19

Max Range: 0.6088. Min Range: -0.6088

Max Act: 0.4129. Min Act: -0.0000

Data Index: 560075 (C4 (Web Text))

Max Activating Token Index: 223