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

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

Neuron 587 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: 0.5163. Min Range: -0.5163

Max Act: 0.5163. Min Act: -0.0000

Data Index: 602669 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.4277. Min Act: -0.0000

Data Index: 446135 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.4123. Min Act: -0.0000

Data Index: 713153 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.4253. Min Act: -0.0000

Data Index: 1282486 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3382. Min Act: -0.0000

Data Index: 435008 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3459. Min Act: -0.0000

Data Index: 465704 (C4 (Web Text))

Max Activating Token Index: 281

Text #6

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3430. Min Act: -0.0000

Data Index: 990997 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3118. Min Act: -0.0000

Data Index: 64838 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3314. Min Act: -0.0000

Data Index: 1117866 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3144. Min Act: -0.0000

Data Index: 382890 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3086. Min Act: -0.0000

Data Index: 1042493 (C4 (Web Text))

Max Activating Token Index: 549

Text #11

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3010. Min Act: -0.0001

Data Index: 1093043 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3085. Min Act: -0.0000

Data Index: 1044225 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.2780. Min Act: -0.0000

Data Index: 349102 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.2946. Min Act: -0.0000

Data Index: 475180 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.3015. Min Act: -0.0000

Data Index: 984775 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.2765. Min Act: -0.0000

Data Index: 300026 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.2682. Min Act: 0.0000

Data Index: 150260 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.2588. Min Act: -0.0001

Data Index: 1091442 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 0.5163. Min Range: -0.5163

Max Act: 0.2588. Min Act: -0.0000

Data Index: 695282 (C4 (Web Text))

Max Activating Token Index: 321