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

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

Neuron 476 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2732. Min Range: -1.2732

Max Act: 1.2732. Min Act: -0.0001

Data Index: 1380542 (Python Code)

Max Activating Token Index: 897

Text #1

Max Range: 1.2732. Min Range: -1.2732

Max Act: 1.2380. Min Act: -0.0001

Data Index: 1190489 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 1.2732. Min Range: -1.2732

Max Act: 1.0833. Min Act: -0.0001

Data Index: 166092 (C4 (Web Text))

Max Activating Token Index: 820

Text #3

Max Range: 1.2732. Min Range: -1.2732

Max Act: 1.0876. Min Act: -0.0001

Data Index: 1156118 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 1.2732. Min Range: -1.2732

Max Act: 1.1394. Min Act: -0.0001

Data Index: 358432 (C4 (Web Text))

Max Activating Token Index: 808

Text #5

Max Range: 1.2732. Min Range: -1.2732

Max Act: 0.9666. Min Act: -0.0001

Data Index: 1498481 (Python Code)

Max Activating Token Index: 317

Text #6

Max Range: 1.2732. Min Range: -1.2732

Max Act: 0.9846. Min Act: -0.0001

Data Index: 549661 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 1.2732. Min Range: -1.2732

Max Act: 0.9850. Min Act: -0.0001

Data Index: 84748 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 1.2732. Min Range: -1.2732

Max Act: 0.9635. Min Act: -0.0001

Data Index: 956235 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 1.2732. Min Range: -1.2732

Max Act: 0.9530. Min Act: -0.0001

Data Index: 1379022 (Python Code)

Max Activating Token Index: 28

Text #10

Max Range: 1.2732. Min Range: -1.2732

Max Act: 0.9722. Min Act: -0.0001

Data Index: 1264376 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 1.2732. Min Range: -1.2732

Max Act: 0.8939. Min Act: -0.0001

Data Index: 573757 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 1.2732. Min Range: -1.2732

Max Act: 0.8837. Min Act: -0.0001

Data Index: 1165936 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 1.2732. Min Range: -1.2732

Max Act: 0.8433. Min Act: -0.0001

Data Index: 1303003 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 1.2732. Min Range: -1.2732

Max Act: 0.8522. Min Act: -0.0001

Data Index: 73646 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 1.2732. Min Range: -1.2732

Max Act: 0.8470. Min Act: -0.0001

Data Index: 1524399 (Python Code)

Max Activating Token Index: 500

Text #16

Max Range: 1.2732. Min Range: -1.2732

Max Act: 0.8432. Min Act: -0.0001

Data Index: 176412 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 1.2732. Min Range: -1.2732

Max Act: 0.7993. Min Act: -0.0001

Data Index: 848855 (C4 (Web Text))

Max Activating Token Index: 206

Text #18

Max Range: 1.2732. Min Range: -1.2732

Max Act: 0.7465. Min Act: -0.0001

Data Index: 1106638 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 1.2732. Min Range: -1.2732

Max Act: 0.8167. Min Act: -0.0001

Data Index: 1444899 (Python Code)

Max Activating Token Index: 88