Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1957 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0508. Min Act: -0.0001

Data Index: 1050310 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0504. Min Act: -0.0001

Data Index: 401027 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0497. Min Act: -0.0001

Data Index: 1250721 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0504. Min Act: -0.0001

Data Index: 13342 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0495. Min Act: -0.0001

Data Index: 611894 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0489. Min Act: -0.0001

Data Index: 1017169 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0492. Min Act: -0.0001

Data Index: 1232300 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0489. Min Act: -0.0001

Data Index: 1259310 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0490. Min Act: -0.0001

Data Index: 270172 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0489. Min Act: -0.0001

Data Index: 1199052 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0485. Min Act: -0.0001

Data Index: 106277 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0483. Min Act: -0.0001

Data Index: 751506 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0484. Min Act: -0.0001

Data Index: 482329 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0481. Min Act: -0.0001

Data Index: 400968 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0479. Min Act: -0.0001

Data Index: 114844 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0485. Min Act: -0.0001

Data Index: 867666 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0478. Min Act: -0.0001

Data Index: 662417 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0471. Min Act: -0.0001

Data Index: 1266681 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0477. Min Act: -0.0001

Data Index: 851050 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0508. Min Range: -0.0508

Max Act: 0.0469. Min Act: -0.0001

Data Index: 300212 (C4 (Web Text))

Max Activating Token Index: 1023