Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 531 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.8771. Min Act: -0.0000

Data Index: 131052 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.4611. Min Act: -0.0000

Data Index: 757092 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.5364. Min Act: -0.0000

Data Index: 592144 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.5859. Min Act: -0.0000

Data Index: 1252762 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.5591. Min Act: -0.0000

Data Index: 1205663 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.4303. Min Act: -0.0000

Data Index: 332222 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.4098. Min Act: -0.0000

Data Index: 928206 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.4660. Min Act: -0.0000

Data Index: 563225 (C4 (Web Text))

Max Activating Token Index: 665

Text #8

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.4706. Min Act: -0.0000

Data Index: 1157260 (C4 (Web Text))

Max Activating Token Index: 514

Text #9

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.3440. Min Act: -0.0000

Data Index: 1261985 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.3439. Min Act: -0.0000

Data Index: 298050 (C4 (Web Text))

Max Activating Token Index: 412

Text #11

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.3210. Min Act: -0.0000

Data Index: 661527 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.3070. Min Act: -0.0000

Data Index: 245839 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.2932. Min Act: -0.0000

Data Index: 471726 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.2734. Min Act: -0.0000

Data Index: 918870 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.2637. Min Act: -0.0000

Data Index: 1169998 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.1827. Min Act: -0.0000

Data Index: 1348204 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.2530. Min Act: -0.0000

Data Index: 646050 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.2423. Min Act: -0.0000

Data Index: 1127630 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 1.8771. Min Range: -1.8771

Max Act: 1.2282. Min Act: -0.0000

Data Index: 285149 (C4 (Web Text))

Max Activating Token Index: 540