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

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

Neuron 3827 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.4557. Min Act: -0.0001

Data Index: 588127 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.3153. Min Act: -0.0001

Data Index: 1250007 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2825. Min Act: -0.0001

Data Index: 676953 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2669. Min Act: -0.0001

Data Index: 947297 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2820. Min Act: -0.0001

Data Index: 1338570 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2581. Min Act: -0.0001

Data Index: 255136 (C4 (Web Text))

Max Activating Token Index: 665

Text #6

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2307. Min Act: -0.0001

Data Index: 803270 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2129. Min Act: -0.0001

Data Index: 81106 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2158. Min Act: -0.0001

Data Index: 1093365 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.1990. Min Act: -0.0001

Data Index: 413282 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.1982. Min Act: -0.0001

Data Index: 1174846 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2324. Min Act: -0.0001

Data Index: 424640 (C4 (Web Text))

Max Activating Token Index: 861

Text #12

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.1932. Min Act: -0.0001

Data Index: 1038160 (C4 (Web Text))

Max Activating Token Index: 383

Text #13

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2021. Min Act: -0.0001

Data Index: 1157473 (C4 (Web Text))

Max Activating Token Index: 332

Text #14

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2106. Min Act: -0.0001

Data Index: 547605 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2173. Min Act: -0.0001

Data Index: 751714 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.2267. Min Act: -0.0001

Data Index: 932049 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.1868. Min Act: -0.0001

Data Index: 298867 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.1742. Min Act: -0.0001

Data Index: 1210985 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 0.4557. Min Range: -0.4557

Max Act: 0.1935. Min Act: -0.0001

Data Index: 402548 (C4 (Web Text))

Max Activating Token Index: 478