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

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

Neuron 4252 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.3507. Min Act: -0.0000

Data Index: 575 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2648. Min Act: -0.0000

Data Index: 152650 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2836. Min Act: -0.0000

Data Index: 632163 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2868. Min Act: -0.0000

Data Index: 984503 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2688. Min Act: -0.0000

Data Index: 466512 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2650. Min Act: -0.0000

Data Index: 629238 (C4 (Web Text))

Max Activating Token Index: 904

Text #6

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2736. Min Act: -0.0000

Data Index: 76769 (C4 (Web Text))

Max Activating Token Index: 548

Text #7

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2913. Min Act: -0.0000

Data Index: 896112 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2808. Min Act: -0.0000

Data Index: 590596 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2621. Min Act: -0.0000

Data Index: 879832 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2774. Min Act: -0.0000

Data Index: 54508 (C4 (Web Text))

Max Activating Token Index: 967

Text #11

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2559. Min Act: -0.0000

Data Index: 274759 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2725. Min Act: -0.0000

Data Index: 1059121 (C4 (Web Text))

Max Activating Token Index: 776

Text #13

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2638. Min Act: -0.0000

Data Index: 829567 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2442. Min Act: -0.0000

Data Index: 626155 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2576. Min Act: -0.0000

Data Index: 1191625 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2638. Min Act: -0.0000

Data Index: 245541 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2464. Min Act: -0.0000

Data Index: 954611 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2697. Min Act: -0.0000

Data Index: 63989 (C4 (Web Text))

Max Activating Token Index: 686

Text #19

Max Range: 0.3507. Min Range: -0.3507

Max Act: 0.2450. Min Act: -0.0000

Data Index: 311434 (C4 (Web Text))

Max Activating Token Index: 205