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

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

Neuron 791 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2857. Min Act: -0.0001

Data Index: 865926 (C4 (Web Text))

Max Activating Token Index: 579

Text #1

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.3020. Min Act: -0.0001

Data Index: 649180 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.3078. Min Act: -0.0001

Data Index: 947935 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2746. Min Act: -0.0001

Data Index: 952880 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2840. Min Act: -0.0000

Data Index: 467048 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2560. Min Act: -0.0001

Data Index: 1337524 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2358. Min Act: -0.0000

Data Index: 1051650 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.3046. Min Act: -0.0001

Data Index: 1151625 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.1958. Min Act: -0.0001

Data Index: 417067 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2374. Min Act: -0.0000

Data Index: 181232 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2455. Min Act: -0.0001

Data Index: 957007 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2198. Min Act: -0.0000

Data Index: 124385 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2265. Min Act: -0.0000

Data Index: 1283422 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2257. Min Act: -0.0000

Data Index: 281224 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2263. Min Act: -0.0001

Data Index: 1116442 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2346. Min Act: -0.0000

Data Index: 223677 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.1853. Min Act: -0.0001

Data Index: 359758 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.1564. Min Act: -0.0001

Data Index: 1111144 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2047. Min Act: -0.0001

Data Index: 1222696 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 0.3078. Min Range: -0.3078

Max Act: 0.2105. Min Act: -0.0001

Data Index: 562430 (C4 (Web Text))

Max Activating Token Index: 441