Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 261 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.2249. Min Act: -0.0000

Data Index: 249278 (The Pile)

Max Activating Token Index: 252

Text #1

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1988. Min Act: -0.0000

Data Index: 805562 (The Pile)

Max Activating Token Index: 780

Text #2

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1930. Min Act: -0.0000

Data Index: 875287 (The Pile)

Max Activating Token Index: 783

Text #3

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1677. Min Act: -0.0000

Data Index: 982047 (The Pile)

Max Activating Token Index: 261

Text #4

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1796. Min Act: -0.0000

Data Index: 737285 (The Pile)

Max Activating Token Index: 924

Text #5

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1904. Min Act: -0.0000

Data Index: 1251104 (The Pile)

Max Activating Token Index: 665

Text #6

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1583. Min Act: -0.0000

Data Index: 983614 (The Pile)

Max Activating Token Index: 683

Text #7

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1835. Min Act: -0.0000

Data Index: 1354750 (The Pile)

Max Activating Token Index: 609

Text #8

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1427. Min Act: -0.0000

Data Index: 1555161 (The Pile)

Max Activating Token Index: 207

Text #9

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1620. Min Act: -0.0000

Data Index: 1664130 (The Pile)

Max Activating Token Index: 849

Text #10

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1609. Min Act: -0.0000

Data Index: 644790 (The Pile)

Max Activating Token Index: 378

Text #11

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1601. Min Act: -0.0000

Data Index: 726141 (The Pile)

Max Activating Token Index: 829

Text #12

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1530. Min Act: -0.0000

Data Index: 902428 (The Pile)

Max Activating Token Index: 376

Text #13

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1485. Min Act: -0.0001

Data Index: 1066985 (The Pile)

Max Activating Token Index: 801

Text #14

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1480. Min Act: -0.0000

Data Index: 490175 (The Pile)

Max Activating Token Index: 251

Text #15

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1554. Min Act: -0.0000

Data Index: 776653 (The Pile)

Max Activating Token Index: 948

Text #16

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1489. Min Act: -0.0000

Data Index: 1155033 (The Pile)

Max Activating Token Index: 591

Text #17

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1373. Min Act: -0.0000

Data Index: 1532151 (The Pile)

Max Activating Token Index: 849

Text #18

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1413. Min Act: -0.0000

Data Index: 856566 (The Pile)

Max Activating Token Index: 562

Text #19

Max Range: 0.2249. Min Range: -0.2249

Max Act: 0.1370. Min Act: -0.0000

Data Index: 798888 (The Pile)

Max Activating Token Index: 363