Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4230 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.3411. Min Act: -0.0001

Data Index: 64744 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.2749. Min Act: -0.0001

Data Index: 708181 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.2538. Min Act: -0.0000

Data Index: 848309 (C4 (Web Text))

Max Activating Token Index: 45

Text #3

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.2696. Min Act: -0.0000

Data Index: 153528 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.2541. Min Act: -0.0001

Data Index: 925440 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.2336. Min Act: -0.0001

Data Index: 1325662 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.2237. Min Act: -0.0001

Data Index: 557972 (C4 (Web Text))

Max Activating Token Index: 102

Text #7

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.2272. Min Act: -0.0001

Data Index: 49791 (C4 (Web Text))

Max Activating Token Index: 777

Text #8

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.2304. Min Act: -0.0000

Data Index: 874686 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.2188. Min Act: -0.0001

Data Index: 893842 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.2059. Min Act: -0.0001

Data Index: 299733 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.2176. Min Act: -0.0001

Data Index: 928109 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.1965. Min Act: -0.0000

Data Index: 819022 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.2066. Min Act: -0.0000

Data Index: 1149768 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.1890. Min Act: -0.0001

Data Index: 1233415 (C4 (Web Text))

Max Activating Token Index: 476

Text #15

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.2065. Min Act: -0.0001

Data Index: 1147679 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.1998. Min Act: -0.0001

Data Index: 930354 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.2026. Min Act: -0.0001

Data Index: 295818 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.1928. Min Act: -0.0001

Data Index: 854681 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 0.3411. Min Range: -0.3411

Max Act: 0.2008. Min Act: -0.0001

Data Index: 655940 (C4 (Web Text))

Max Activating Token Index: 949