Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2441 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 3.0525. Min Range: -3.0525

Max Act: 3.0525. Min Act: -0.0001

Data Index: 1030828 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 3.0525. Min Range: -3.0525

Max Act: 3.0237. Min Act: -0.0001

Data Index: 781457 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.9124. Min Act: -0.0001

Data Index: 326769 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.0863. Min Act: -0.0001

Data Index: 820567 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.3173. Min Act: -0.0001

Data Index: 1115614 (C4 (Web Text))

Max Activating Token Index: 596

Text #5

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.2601. Min Act: -0.0001

Data Index: 153308 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.2765. Min Act: -0.0001

Data Index: 789263 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.2338. Min Act: -0.0001

Data Index: 407892 (C4 (Web Text))

Max Activating Token Index: 266

Text #8

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.2328. Min Act: -0.0001

Data Index: 1003489 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.1813. Min Act: -0.0001

Data Index: 597349 (C4 (Web Text))

Max Activating Token Index: 1014

Text #10

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.5051. Min Act: -0.0001

Data Index: 669941 (C4 (Web Text))

Max Activating Token Index: 684

Text #11

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.0597. Min Act: -0.0001

Data Index: 723738 (C4 (Web Text))

Max Activating Token Index: 183

Text #12

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.1662. Min Act: -0.0001

Data Index: 879075 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.1598. Min Act: -0.0001

Data Index: 315718 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.1635. Min Act: -0.0001

Data Index: 1340689 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.1542. Min Act: -0.0001

Data Index: 86088 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 3.0525. Min Range: -3.0525

Max Act: 1.7239. Min Act: -0.0001

Data Index: 1244942 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.2508. Min Act: -0.0001

Data Index: 97137 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.2239. Min Act: -0.0001

Data Index: 475887 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 3.0525. Min Range: -3.0525

Max Act: 2.2250. Min Act: -0.0001

Data Index: 1354534 (C4 (Web Text))

Max Activating Token Index: 120