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

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

Neuron 1399 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0330. Min Range: -2.0330

Max Act: 2.0330. Min Act: -0.0001

Data Index: 78901 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 2.0330. Min Range: -2.0330

Max Act: 1.7792. Min Act: -0.0000

Data Index: 875263 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 2.0330. Min Range: -2.0330

Max Act: 1.7365. Min Act: -0.0001

Data Index: 787361 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 2.0330. Min Range: -2.0330

Max Act: 1.6953. Min Act: -0.0001

Data Index: 1124481 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 2.0330. Min Range: -2.0330

Max Act: 1.6920. Min Act: -0.0000

Data Index: 965728 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 2.0330. Min Range: -2.0330

Max Act: 1.4349. Min Act: -0.0000

Data Index: 783480 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 2.0330. Min Range: -2.0330

Max Act: 1.4606. Min Act: -0.0001

Data Index: 1639645 (Python Code)

Max Activating Token Index: 131

Text #7

Max Range: 2.0330. Min Range: -2.0330

Max Act: 1.4680. Min Act: -0.0000

Data Index: 924298 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 2.0330. Min Range: -2.0330

Max Act: 1.4861. Min Act: -0.0000

Data Index: 766639 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 2.0330. Min Range: -2.0330

Max Act: 1.3726. Min Act: -0.0001

Data Index: 283147 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 2.0330. Min Range: -2.0330

Max Act: 1.3883. Min Act: -0.0001

Data Index: 1018859 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 2.0330. Min Range: -2.0330

Max Act: 1.2933. Min Act: -0.0000

Data Index: 1316255 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 2.0330. Min Range: -2.0330

Max Act: 1.2009. Min Act: -0.0000

Data Index: 714120 (C4 (Web Text))

Max Activating Token Index: 728

Text #13

Max Range: 2.0330. Min Range: -2.0330

Max Act: 1.1824. Min Act: -0.0000

Data Index: 895045 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 2.0330. Min Range: -2.0330

Max Act: 1.2310. Min Act: -0.0001

Data Index: 1278958 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 2.0330. Min Range: -2.0330

Max Act: 1.2390. Min Act: -0.0000

Data Index: 1107424 (C4 (Web Text))

Max Activating Token Index: 997

Text #16

Max Range: 2.0330. Min Range: -2.0330

Max Act: 1.0851. Min Act: -0.0000

Data Index: 1127667 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 2.0330. Min Range: -2.0330

Max Act: 1.0073. Min Act: -0.0000

Data Index: 1181489 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 2.0330. Min Range: -2.0330

Max Act: 1.1621. Min Act: -0.0000

Data Index: 943547 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 2.0330. Min Range: -2.0330

Max Act: 1.0877. Min Act: -0.0000

Data Index: 1266818 (C4 (Web Text))

Max Activating Token Index: 971