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

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

Neuron 4037 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: 0.4042. Min Range: -0.4042

Max Act: 0.4042. Min Act: -0.0001

Data Index: 495243 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.3500. Min Act: -0.0002

Data Index: 621563 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.3400. Min Act: -0.0001

Data Index: 1191408 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.3187. Min Act: -0.0002

Data Index: 728984 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.3038. Min Act: -0.0001

Data Index: 1057822 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.3117. Min Act: -0.0002

Data Index: 386177 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.3213. Min Act: -0.0002

Data Index: 662275 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.3010. Min Act: -0.0001

Data Index: 390914 (C4 (Web Text))

Max Activating Token Index: 427

Text #8

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.2985. Min Act: -0.0002

Data Index: 131883 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.2760. Min Act: -0.0002

Data Index: 519781 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.3023. Min Act: -0.0002

Data Index: 791352 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.3006. Min Act: -0.0001

Data Index: 1325453 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.2993. Min Act: -0.0002

Data Index: 97544 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.2982. Min Act: -0.0002

Data Index: 343741 (C4 (Web Text))

Max Activating Token Index: 81

Text #14

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.3000. Min Act: -0.0001

Data Index: 499422 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.2839. Min Act: -0.0001

Data Index: 1110500 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.2780. Min Act: -0.0002

Data Index: 412632 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.2611. Min Act: -0.0001

Data Index: 155620 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.2777. Min Act: -0.0002

Data Index: 976180 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 0.4042. Min Range: -0.4042

Max Act: 0.2659. Min Act: -0.0001

Data Index: 577308 (C4 (Web Text))

Max Activating Token Index: 44