Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5429 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.6429. Min Act: -0.0002

Data Index: 1026791 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.5668. Min Act: -0.0002

Data Index: 1247613 (C4 (Web Text))

Max Activating Token Index: 69

Text #2

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.4998. Min Act: -0.0002

Data Index: 1333548 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.5421. Min Act: -0.0002

Data Index: 1132706 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.4825. Min Act: -0.0002

Data Index: 506940 (C4 (Web Text))

Max Activating Token Index: 414

Text #5

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.3857. Min Act: -0.0002

Data Index: 506756 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.3776. Min Act: -0.0002

Data Index: 181845 (C4 (Web Text))

Max Activating Token Index: 87

Text #7

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.4075. Min Act: -0.0002

Data Index: 143412 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.3506. Min Act: -0.0002

Data Index: 998654 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.3483. Min Act: -0.0002

Data Index: 1009026 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.3052. Min Act: -0.0002

Data Index: 824305 (C4 (Web Text))

Max Activating Token Index: 12

Text #11

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.2935. Min Act: -0.0002

Data Index: 1149544 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.3628. Min Act: -0.0002

Data Index: 452449 (C4 (Web Text))

Max Activating Token Index: 220

Text #13

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.3928. Min Act: -0.0002

Data Index: 763534 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.3146. Min Act: -0.0002

Data Index: 938612 (C4 (Web Text))

Max Activating Token Index: 225

Text #15

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.3041. Min Act: -0.0002

Data Index: 787215 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.3052. Min Act: -0.0002

Data Index: 1266822 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.2725. Min Act: -0.0002

Data Index: 1180474 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.2767. Min Act: -0.0002

Data Index: 389489 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 1.6429. Min Range: -1.6429

Max Act: 1.2582. Min Act: -0.0002

Data Index: 853224 (C4 (Web Text))

Max Activating Token Index: 255