Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3349 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.3165. Min Act: 0.0000

Data Index: 319879 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2979. Min Act: -0.0000

Data Index: 496726 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.3057. Min Act: 0.0000

Data Index: 990876 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.3049. Min Act: -0.0000

Data Index: 662832 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2913. Min Act: 0.0001

Data Index: 1359568 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2980. Min Act: -0.0000

Data Index: 1076393 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2965. Min Act: -0.0000

Data Index: 858050 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.3070. Min Act: -0.0000

Data Index: 119254 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2964. Min Act: -0.0000

Data Index: 938493 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2951. Min Act: -0.0000

Data Index: 725599 (C4 (Web Text))

Max Activating Token Index: 665

Text #10

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2832. Min Act: -0.0000

Data Index: 1084258 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2919. Min Act: -0.0000

Data Index: 262003 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2910. Min Act: -0.0000

Data Index: 665307 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.3012. Min Act: -0.0000

Data Index: 29011 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2877. Min Act: 0.0000

Data Index: 553538 (C4 (Web Text))

Max Activating Token Index: 802

Text #15

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2830. Min Act: -0.0000

Data Index: 175104 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2734. Min Act: 0.0001

Data Index: 810087 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2793. Min Act: -0.0000

Data Index: 1188409 (C4 (Web Text))

Max Activating Token Index: 756

Text #18

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2790. Min Act: -0.0000

Data Index: 579339 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.3165. Min Range: -0.3165

Max Act: 0.2707. Min Act: -0.0000

Data Index: 593073 (C4 (Web Text))

Max Activating Token Index: 635