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

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

Neuron 907 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: 0.6552. Min Range: -0.6552

Max Act: 0.6552. Min Act: -0.0000

Data Index: 180095 (C4 (Web Text))

Max Activating Token Index: 531

Text #1

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.6196. Min Act: -0.0000

Data Index: 1069091 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.6011. Min Act: -0.0000

Data Index: 861765 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.6001. Min Act: -0.0000

Data Index: 287406 (C4 (Web Text))

Max Activating Token Index: 352

Text #4

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.6306. Min Act: -0.0001

Data Index: 23819 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5985. Min Act: -0.0000

Data Index: 262931 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5489. Min Act: -0.0000

Data Index: 249255 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5404. Min Act: -0.0000

Data Index: 62368 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5224. Min Act: -0.0000

Data Index: 1345460 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5379. Min Act: -0.0000

Data Index: 897083 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5206. Min Act: -0.0000

Data Index: 726849 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5298. Min Act: -0.0000

Data Index: 946950 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5397. Min Act: -0.0000

Data Index: 90872 (C4 (Web Text))

Max Activating Token Index: 494

Text #13

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5214. Min Act: -0.0000

Data Index: 387249 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5183. Min Act: -0.0001

Data Index: 502768 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5318. Min Act: -0.0000

Data Index: 665384 (C4 (Web Text))

Max Activating Token Index: 726

Text #16

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.4819. Min Act: -0.0000

Data Index: 527708 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5138. Min Act: -0.0000

Data Index: 1305669 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5097. Min Act: -0.0000

Data Index: 739621 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 0.6552. Min Range: -0.6552

Max Act: 0.5243. Min Act: -0.0001

Data Index: 86702 (C4 (Web Text))

Max Activating Token Index: 398