Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1871 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0582. Min Act: -0.0006

Data Index: 1308994 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0551. Min Act: -0.0006

Data Index: 986770 (C4 (Web Text))

Max Activating Token Index: 184

Text #2

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0592. Min Act: -0.0006

Data Index: 966174 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0541. Min Act: -0.0006

Data Index: 728984 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0568. Min Act: -0.0006

Data Index: 195017 (C4 (Web Text))

Max Activating Token Index: 201

Text #5

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0544. Min Act: -0.0006

Data Index: 656381 (C4 (Web Text))

Max Activating Token Index: 645

Text #6

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0510. Min Act: -0.0006

Data Index: 978228 (C4 (Web Text))

Max Activating Token Index: 942

Text #7

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0521. Min Act: -0.0006

Data Index: 1070298 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0495. Min Act: -0.0006

Data Index: 380611 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0507. Min Act: -0.0006

Data Index: 190911 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0507. Min Act: -0.0006

Data Index: 638759 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0512. Min Act: -0.0006

Data Index: 187870 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0497. Min Act: -0.0006

Data Index: 207551 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0471. Min Act: -0.0006

Data Index: 486267 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0489. Min Act: -0.0006

Data Index: 794393 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0470. Min Act: -0.0006

Data Index: 1270629 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0512. Min Act: -0.0006

Data Index: 617746 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0490. Min Act: -0.0006

Data Index: 1267267 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0485. Min Act: -0.0006

Data Index: 180710 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.0592. Min Range: -0.0592

Max Act: 0.0485. Min Act: -0.0006

Data Index: 40544 (C4 (Web Text))

Max Activating Token Index: 795