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

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

Neuron 3638 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6347. Min Range: -2.6347

Max Act: 2.6347. Min Act: -0.0000

Data Index: 944089 (C4 (Web Text))

Max Activating Token Index: 636

Text #1

Max Range: 2.6347. Min Range: -2.6347

Max Act: 2.4689. Min Act: -0.0000

Data Index: 280310 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 2.6347. Min Range: -2.6347

Max Act: 2.1337. Min Act: -0.0000

Data Index: 738425 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 2.6347. Min Range: -2.6347

Max Act: 2.0901. Min Act: -0.0000

Data Index: 1343570 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 2.6347. Min Range: -2.6347

Max Act: 2.3546. Min Act: -0.0000

Data Index: 783386 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 2.6347. Min Range: -2.6347

Max Act: 2.0524. Min Act: -0.0000

Data Index: 56998 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 2.6347. Min Range: -2.6347

Max Act: 2.0569. Min Act: -0.0000

Data Index: 747360 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 2.6347. Min Range: -2.6347

Max Act: 2.0148. Min Act: -0.0000

Data Index: 458613 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 2.6347. Min Range: -2.6347

Max Act: 1.9017. Min Act: -0.0000

Data Index: 984931 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 2.6347. Min Range: -2.6347

Max Act: 1.9892. Min Act: -0.0000

Data Index: 91616 (C4 (Web Text))

Max Activating Token Index: 90

Text #10

Max Range: 2.6347. Min Range: -2.6347

Max Act: 1.9690. Min Act: -0.0000

Data Index: 827761 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 2.6347. Min Range: -2.6347

Max Act: 1.8613. Min Act: -0.0000

Data Index: 743170 (C4 (Web Text))

Max Activating Token Index: 453

Text #12

Max Range: 2.6347. Min Range: -2.6347

Max Act: 1.9677. Min Act: -0.0000

Data Index: 482003 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 2.6347. Min Range: -2.6347

Max Act: 1.9619. Min Act: -0.0000

Data Index: 158656 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 2.6347. Min Range: -2.6347

Max Act: 1.8366. Min Act: -0.0000

Data Index: 4862 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 2.6347. Min Range: -2.6347

Max Act: 1.9562. Min Act: -0.0000

Data Index: 309150 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 2.6347. Min Range: -2.6347

Max Act: 1.8166. Min Act: -0.0000

Data Index: 1107171 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 2.6347. Min Range: -2.6347

Max Act: 1.8814. Min Act: -0.0000

Data Index: 948742 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 2.6347. Min Range: -2.6347

Max Act: 1.8736. Min Act: -0.0000

Data Index: 142604 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 2.6347. Min Range: -2.6347

Max Act: 1.7528. Min Act: -0.0000

Data Index: 177854 (C4 (Web Text))

Max Activating Token Index: 186