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

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

Neuron 3492 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: 0.7442. Min Range: -0.7442

Max Act: 0.7442. Min Act: -0.0000

Data Index: 954315 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.5642. Min Act: -0.0000

Data Index: 281929 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.5686. Min Act: -0.0000

Data Index: 212796 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.6181. Min Act: -0.0000

Data Index: 887171 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.5418. Min Act: -0.0000

Data Index: 54153 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.5657. Min Act: -0.0000

Data Index: 540836 (C4 (Web Text))

Max Activating Token Index: 30

Text #6

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.5474. Min Act: -0.0000

Data Index: 1255073 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.5418. Min Act: -0.0000

Data Index: 1164323 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.5151. Min Act: -0.0001

Data Index: 1270530 (C4 (Web Text))

Max Activating Token Index: 977

Text #9

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.5102. Min Act: -0.0000

Data Index: 945453 (C4 (Web Text))

Max Activating Token Index: 740

Text #10

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.4948. Min Act: -0.0000

Data Index: 225212 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.5209. Min Act: -0.0000

Data Index: 1254156 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.5042. Min Act: -0.0000

Data Index: 288934 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.5288. Min Act: -0.0000

Data Index: 731690 (C4 (Web Text))

Max Activating Token Index: 384

Text #14

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.4926. Min Act: -0.0000

Data Index: 219580 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.4918. Min Act: -0.0000

Data Index: 1309068 (C4 (Web Text))

Max Activating Token Index: 425

Text #16

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.5403. Min Act: -0.0000

Data Index: 517728 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.4870. Min Act: -0.0000

Data Index: 1046499 (C4 (Web Text))

Max Activating Token Index: 566

Text #18

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.4641. Min Act: -0.0001

Data Index: 77031 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 0.7442. Min Range: -0.7442

Max Act: 0.4497. Min Act: -0.0000

Data Index: 603192 (C4 (Web Text))

Max Activating Token Index: 972