Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1435 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.9407. Min Act: -0.0000

Data Index: 967984 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.7592. Min Act: -0.0000

Data Index: 277651 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.7984. Min Act: -0.0000

Data Index: 128691 (C4 (Web Text))

Max Activating Token Index: 395

Text #3

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.7689. Min Act: -0.0000

Data Index: 1207000 (C4 (Web Text))

Max Activating Token Index: 957

Text #4

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.6895. Min Act: -0.0000

Data Index: 342212 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.7640. Min Act: -0.0000

Data Index: 567753 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.7401. Min Act: -0.0000

Data Index: 29611 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.6935. Min Act: -0.0000

Data Index: 1108316 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.7021. Min Act: -0.0000

Data Index: 852162 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.6970. Min Act: -0.0000

Data Index: 426568 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.7135. Min Act: -0.0000

Data Index: 292972 (C4 (Web Text))

Max Activating Token Index: 268

Text #11

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.6192. Min Act: -0.0000

Data Index: 449661 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.6350. Min Act: -0.0000

Data Index: 419333 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.6552. Min Act: -0.0000

Data Index: 1236917 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.6426. Min Act: -0.0000

Data Index: 1269994 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.5991. Min Act: -0.0000

Data Index: 149969 (C4 (Web Text))

Max Activating Token Index: 17

Text #16

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.6131. Min Act: -0.0000

Data Index: 221494 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.6022. Min Act: -0.0000

Data Index: 139902 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.5444. Min Act: -0.0000

Data Index: 37044 (C4 (Web Text))

Max Activating Token Index: 231

Text #19

Max Range: 0.9407. Min Range: -0.9407

Max Act: 0.5787. Min Act: -0.0000

Data Index: 304433 (C4 (Web Text))

Max Activating Token Index: 999