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

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

Neuron 922 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.9622. Min Act: -0.0004

Data Index: 652361 (C4 (Web Text))

Max Activating Token Index: 685

Text #1

Max Range: 1.1526. Min Range: -1.1526

Max Act: 1.1526. Min Act: -0.0004

Data Index: 790080 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 1.1526. Min Range: -1.1526

Max Act: 1.0346. Min Act: -0.0004

Data Index: 174687 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 1.1526. Min Range: -1.1526

Max Act: 1.0028. Min Act: -0.0004

Data Index: 1316441 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.8497. Min Act: -0.0004

Data Index: 25664 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.9897. Min Act: -0.0004

Data Index: 885639 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.9861. Min Act: -0.0004

Data Index: 1289457 (C4 (Web Text))

Max Activating Token Index: 479

Text #7

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.8682. Min Act: -0.0004

Data Index: 207591 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.9755. Min Act: -0.0004

Data Index: 1323239 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.9030. Min Act: -0.0004

Data Index: 810439 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.8432. Min Act: -0.0004

Data Index: 1274237 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 1.1526. Min Range: -1.1526

Max Act: 1.0328. Min Act: -0.0004

Data Index: 853541 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.8743. Min Act: -0.0004

Data Index: 428322 (C4 (Web Text))

Max Activating Token Index: 213

Text #13

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.7915. Min Act: -0.0004

Data Index: 1078749 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.9863. Min Act: -0.0004

Data Index: 296882 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.8397. Min Act: -0.0004

Data Index: 1173259 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.9480. Min Act: -0.0004

Data Index: 1125795 (C4 (Web Text))

Max Activating Token Index: 700

Text #17

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.9808. Min Act: -0.0004

Data Index: 245536 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.9170. Min Act: -0.0004

Data Index: 92397 (C4 (Web Text))

Max Activating Token Index: 98

Text #19

Max Range: 1.1526. Min Range: -1.1526

Max Act: 0.8577. Min Act: -0.0004

Data Index: 1331955 (C4 (Web Text))

Max Activating Token Index: 122