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

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

Neuron 1842 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: 0.3747. Min Range: -0.3747

Max Act: 0.3747. Min Act: -0.0000

Data Index: 1327306 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.3073. Min Act: -0.0000

Data Index: 900443 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.3177. Min Act: -0.0000

Data Index: 1028789 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.3157. Min Act: -0.0000

Data Index: 813712 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.3151. Min Act: -0.0000

Data Index: 711680 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.3215. Min Act: -0.0000

Data Index: 1194858 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.3158. Min Act: -0.0000

Data Index: 1144333 (C4 (Web Text))

Max Activating Token Index: 978

Text #7

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2868. Min Act: -0.0000

Data Index: 15554 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2839. Min Act: -0.0001

Data Index: 172928 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2814. Min Act: -0.0000

Data Index: 1182250 (C4 (Web Text))

Max Activating Token Index: 497

Text #10

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2860. Min Act: -0.0000

Data Index: 37845 (C4 (Web Text))

Max Activating Token Index: 131

Text #11

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2843. Min Act: -0.0000

Data Index: 1290342 (C4 (Web Text))

Max Activating Token Index: 575

Text #12

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2824. Min Act: -0.0001

Data Index: 1062797 (C4 (Web Text))

Max Activating Token Index: 465

Text #13

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2785. Min Act: -0.0000

Data Index: 1098243 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2711. Min Act: -0.0000

Data Index: 43350 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2612. Min Act: -0.0000

Data Index: 1258755 (C4 (Web Text))

Max Activating Token Index: 551

Text #16

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2592. Min Act: -0.0000

Data Index: 1149918 (C4 (Web Text))

Max Activating Token Index: 307

Text #17

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2610. Min Act: -0.0001

Data Index: 639509 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2449. Min Act: -0.0001

Data Index: 1128257 (C4 (Web Text))

Max Activating Token Index: 954

Text #19

Max Range: 0.3747. Min Range: -0.3747

Max Act: 0.2433. Min Act: -0.0000

Data Index: 885702 (C4 (Web Text))

Max Activating Token Index: 554