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

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

Neuron 1268 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7166. Min Range: -1.7166

Max Act: 1.6856. Min Act: -0.0001

Data Index: 762578 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 1.7166. Min Range: -1.7166

Max Act: 1.7166. Min Act: -0.0001

Data Index: 305422 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 1.7166. Min Range: -1.7166

Max Act: 1.3244. Min Act: -0.0001

Data Index: 1154085 (C4 (Web Text))

Max Activating Token Index: 944

Text #3

Max Range: 1.7166. Min Range: -1.7166

Max Act: 1.3048. Min Act: -0.0001

Data Index: 1080041 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 1.7166. Min Range: -1.7166

Max Act: 1.4691. Min Act: -0.0001

Data Index: 69472 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 1.7166. Min Range: -1.7166

Max Act: 1.2505. Min Act: -0.0001

Data Index: 977863 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 1.7166. Min Range: -1.7166

Max Act: 1.4430. Min Act: -0.0002

Data Index: 993471 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 1.7166. Min Range: -1.7166

Max Act: 1.3136. Min Act: -0.0001

Data Index: 850537 (C4 (Web Text))

Max Activating Token Index: 383

Text #8

Max Range: 1.7166. Min Range: -1.7166

Max Act: 1.3108. Min Act: -0.0001

Data Index: 1002829 (C4 (Web Text))

Max Activating Token Index: 957

Text #9

Max Range: 1.7166. Min Range: -1.7166

Max Act: 1.3273. Min Act: -0.0001

Data Index: 286034 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 1.7166. Min Range: -1.7166

Max Act: 1.3233. Min Act: -0.0002

Data Index: 1146369 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 1.7166. Min Range: -1.7166

Max Act: 1.1662. Min Act: -0.0001

Data Index: 693186 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 1.7166. Min Range: -1.7166

Max Act: 1.2297. Min Act: -0.0002

Data Index: 211474 (C4 (Web Text))

Max Activating Token Index: 163

Text #13

Max Range: 1.7166. Min Range: -1.7166

Max Act: 1.3037. Min Act: -0.0002

Data Index: 1359177 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 1.7166. Min Range: -1.7166

Max Act: 1.1418. Min Act: -0.0002

Data Index: 68587 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 1.7166. Min Range: -1.7166

Max Act: 1.2771. Min Act: -0.0002

Data Index: 209607 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 1.7166. Min Range: -1.7166

Max Act: 1.1894. Min Act: -0.0001

Data Index: 947940 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 1.7166. Min Range: -1.7166

Max Act: 1.3019. Min Act: -0.0001

Data Index: 121753 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 1.7166. Min Range: -1.7166

Max Act: 1.1503. Min Act: -0.0001

Data Index: 552758 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 1.7166. Min Range: -1.7166

Max Act: 1.2363. Min Act: -0.0001

Data Index: 136819 (C4 (Web Text))

Max Activating Token Index: 149