Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2356 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2529. Min Range: -0.2529

Max Act: 0.2529. Min Act: -0.0003

Data Index: 844844 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 0.2529. Min Range: -0.2529

Max Act: 0.2285. Min Act: -0.0003

Data Index: 1255883 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 0.2529. Min Range: -0.2529

Max Act: 0.2287. Min Act: -0.0003

Data Index: 683770 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 0.2529. Min Range: -0.2529

Max Act: 0.2279. Min Act: -0.0003

Data Index: 274221 (C4 (Web Text))

Max Activating Token Index: 821

Text #4

Max Range: 0.2529. Min Range: -0.2529

Max Act: 0.2212. Min Act: -0.0003

Data Index: 88140 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 0.2529. Min Range: -0.2529

Max Act: 0.2258. Min Act: -0.0003

Data Index: 531930 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.2529. Min Range: -0.2529

Max Act: 0.2111. Min Act: -0.0003

Data Index: 1096439 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 0.2529. Min Range: -0.2529

Max Act: 0.2108. Min Act: -0.0003

Data Index: 195574 (C4 (Web Text))

Max Activating Token Index: 396

Text #8

Max Range: 0.2529. Min Range: -0.2529

Max Act: 0.2018. Min Act: -0.0003

Data Index: 924403 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.2529. Min Range: -0.2529

Max Act: 0.2022. Min Act: -0.0003

Data Index: 631575 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 0.2529. Min Range: -0.2529

Max Act: 0.1957. Min Act: -0.0003

Data Index: 310979 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 0.2529. Min Range: -0.2529

Max Act: 0.1925. Min Act: -0.0003

Data Index: 295587 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 0.2529. Min Range: -0.2529

Max Act: 0.1999. Min Act: -0.0003

Data Index: 33674 (C4 (Web Text))

Max Activating Token Index: 794

Text #13

Max Range: 0.2529. Min Range: -0.2529

Max Act: 0.1902. Min Act: -0.0003

Data Index: 754238 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 0.2529. Min Range: -0.2529

Max Act: 0.2047. Min Act: -0.0003

Data Index: 657848 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 0.2529. Min Range: -0.2529

Max Act: 0.2257. Min Act: -0.0003

Data Index: 1116363 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 0.2529. Min Range: -0.2529

Max Act: 0.2093. Min Act: -0.0003

Data Index: 656556 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 0.2529. Min Range: -0.2529

Max Act: 0.1942. Min Act: -0.0003

Data Index: 128453 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 0.2529. Min Range: -0.2529

Max Act: 0.1993. Min Act: -0.0003

Data Index: 1347573 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.2529. Min Range: -0.2529

Max Act: 0.2130. Min Act: -0.0003

Data Index: 824826 (C4 (Web Text))

Max Activating Token Index: 625