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

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

Neuron 569 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3761. Min Act: -0.0002

Data Index: 184147 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.4041. Min Act: -0.0001

Data Index: 674047 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.4049. Min Act: -0.0002

Data Index: 382486 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3400. Min Act: -0.0002

Data Index: 1068894 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3528. Min Act: -0.0001

Data Index: 804152 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3728. Min Act: -0.0002

Data Index: 242200 (C4 (Web Text))

Max Activating Token Index: 505

Text #6

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3389. Min Act: -0.0002

Data Index: 57092 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3779. Min Act: -0.0002

Data Index: 1330740 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3514. Min Act: -0.0002

Data Index: 170809 (C4 (Web Text))

Max Activating Token Index: 133

Text #9

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3412. Min Act: -0.0002

Data Index: 1332567 (C4 (Web Text))

Max Activating Token Index: 502

Text #10

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3527. Min Act: -0.0002

Data Index: 865514 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3093. Min Act: -0.0002

Data Index: 983733 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3452. Min Act: -0.0002

Data Index: 1115389 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3448. Min Act: -0.0002

Data Index: 439555 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3026. Min Act: -0.0001

Data Index: 1039338 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.2832. Min Act: -0.0001

Data Index: 1327601 (C4 (Web Text))

Max Activating Token Index: 181

Text #16

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.2993. Min Act: -0.0001

Data Index: 664910 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3156. Min Act: -0.0002

Data Index: 550610 (C4 (Web Text))

Max Activating Token Index: 389

Text #18

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.2864. Min Act: -0.0002

Data Index: 655899 (C4 (Web Text))

Max Activating Token Index: 293

Text #19

Max Range: 0.4049. Min Range: -0.4049

Max Act: 0.3311. Min Act: -0.0001

Data Index: 142837 (C4 (Web Text))

Max Activating Token Index: 984