Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 661 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0605. Min Range: -1.0605

Max Act: 1.0078. Min Act: -0.0001

Data Index: 107491 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 1.0605. Min Range: -1.0605

Max Act: 1.0198. Min Act: -0.0001

Data Index: 520905 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 1.0605. Min Range: -1.0605

Max Act: 1.0605. Min Act: -0.0001

Data Index: 685218 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.9119. Min Act: -0.0001

Data Index: 257053 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.9680. Min Act: -0.0001

Data Index: 528438 (C4 (Web Text))

Max Activating Token Index: 242

Text #5

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.8427. Min Act: -0.0001

Data Index: 247252 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.7870. Min Act: -0.0001

Data Index: 337788 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.8475. Min Act: -0.0001

Data Index: 564831 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.7495. Min Act: -0.0001

Data Index: 418387 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.8017. Min Act: -0.0001

Data Index: 414909 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.7478. Min Act: -0.0001

Data Index: 476560 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.7980. Min Act: -0.0001

Data Index: 293664 (C4 (Web Text))

Max Activating Token Index: 195

Text #12

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.8030. Min Act: -0.0001

Data Index: 200371 (C4 (Web Text))

Max Activating Token Index: 456

Text #13

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.8495. Min Act: -0.0001

Data Index: 1223138 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.7748. Min Act: -0.0001

Data Index: 37241 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.7990. Min Act: -0.0001

Data Index: 327929 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.7978. Min Act: -0.0001

Data Index: 1152220 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.7993. Min Act: -0.0001

Data Index: 387426 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.7246. Min Act: -0.0001

Data Index: 1026082 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 1.0605. Min Range: -1.0605

Max Act: 0.8405. Min Act: -0.0001

Data Index: 499824 (C4 (Web Text))

Max Activating Token Index: 886