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

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

Neuron 2893 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.4337. Min Act: -0.0000

Data Index: 557546 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.4162. Min Act: -0.0000

Data Index: 1353494 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3593. Min Act: -0.0000

Data Index: 1020408 (C4 (Web Text))

Max Activating Token Index: 631

Text #3

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3784. Min Act: -0.0000

Data Index: 684630 (C4 (Web Text))

Max Activating Token Index: 564

Text #4

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3649. Min Act: -0.0000

Data Index: 261599 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3857. Min Act: -0.0000

Data Index: 13126 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3308. Min Act: -0.0000

Data Index: 117842 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3658. Min Act: -0.0000

Data Index: 763038 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3286. Min Act: -0.0000

Data Index: 816826 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3212. Min Act: -0.0000

Data Index: 23875 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3075. Min Act: -0.0000

Data Index: 635775 (C4 (Web Text))

Max Activating Token Index: 879

Text #11

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3085. Min Act: -0.0000

Data Index: 621759 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.2840. Min Act: -0.0000

Data Index: 669268 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3150. Min Act: -0.0000

Data Index: 736978 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3040. Min Act: -0.0000

Data Index: 1181802 (C4 (Web Text))

Max Activating Token Index: 115

Text #15

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.3326. Min Act: -0.0000

Data Index: 1314960 (C4 (Web Text))

Max Activating Token Index: 914

Text #16

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.2826. Min Act: -0.0000

Data Index: 1279258 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.2914. Min Act: -0.0000

Data Index: 1298887 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.2873. Min Act: -0.0000

Data Index: 644394 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 0.4337. Min Range: -0.4337

Max Act: 0.2804. Min Act: -0.0000

Data Index: 942819 (C4 (Web Text))

Max Activating Token Index: 996