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

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

Neuron 2405 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0712. Min Act: -0.0001

Data Index: 1356883 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0666. Min Act: -0.0001

Data Index: 668348 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0641. Min Act: -0.0001

Data Index: 868545 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0594. Min Act: -0.0001

Data Index: 887350 (C4 (Web Text))

Max Activating Token Index: 931

Text #4

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0629. Min Act: -0.0001

Data Index: 854111 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0571. Min Act: -0.0001

Data Index: 335867 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0519. Min Act: -0.0001

Data Index: 903469 (C4 (Web Text))

Max Activating Token Index: 846

Text #7

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0504. Min Act: -0.0001

Data Index: 1310136 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0500. Min Act: -0.0001

Data Index: 790203 (C4 (Web Text))

Max Activating Token Index: 414

Text #9

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0467. Min Act: -0.0001

Data Index: 1232623 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0438. Min Act: -0.0001

Data Index: 449389 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0486. Min Act: -0.0001

Data Index: 654702 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0464. Min Act: -0.0001

Data Index: 854774 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0471. Min Act: -0.0001

Data Index: 852088 (C4 (Web Text))

Max Activating Token Index: 931

Text #14

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0410. Min Act: -0.0001

Data Index: 1006678 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0455. Min Act: -0.0001

Data Index: 84652 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0470. Min Act: -0.0001

Data Index: 1175136 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0433. Min Act: -0.0001

Data Index: 67063 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0448. Min Act: -0.0001

Data Index: 1103328 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 0.0712. Min Range: -0.0712

Max Act: 0.0462. Min Act: -0.0002

Data Index: 1129148 (C4 (Web Text))

Max Activating Token Index: 950