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

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

Neuron 2127 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: 0.3585. Min Range: -0.3585

Max Act: 0.3335. Min Act: -0.0001

Data Index: 859241 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3585. Min Act: -0.0002

Data Index: 692535 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3214. Min Act: -0.0002

Data Index: 407690 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3324. Min Act: -0.0002

Data Index: 225613 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3127. Min Act: -0.0001

Data Index: 912471 (C4 (Web Text))

Max Activating Token Index: 100

Text #5

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3087. Min Act: -0.0002

Data Index: 824771 (C4 (Web Text))

Max Activating Token Index: 631

Text #6

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3124. Min Act: -0.0002

Data Index: 232793 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3036. Min Act: -0.0001

Data Index: 299959 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3177. Min Act: -0.0001

Data Index: 704406 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3079. Min Act: -0.0002

Data Index: 1273610 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3151. Min Act: -0.0001

Data Index: 623555 (C4 (Web Text))

Max Activating Token Index: 919

Text #11

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3102. Min Act: -0.0001

Data Index: 508889 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3211. Min Act: -0.0001

Data Index: 903464 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.3065. Min Act: -0.0001

Data Index: 973327 (C4 (Web Text))

Max Activating Token Index: 295

Text #14

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2947. Min Act: -0.0002

Data Index: 1152571 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2818. Min Act: -0.0001

Data Index: 673611 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2797. Min Act: -0.0002

Data Index: 244401 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2740. Min Act: -0.0002

Data Index: 578108 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2681. Min Act: -0.0002

Data Index: 121757 (C4 (Web Text))

Max Activating Token Index: 529

Text #19

Max Range: 0.3585. Min Range: -0.3585

Max Act: 0.2710. Min Act: -0.0002

Data Index: 725473 (C4 (Web Text))

Max Activating Token Index: 236