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

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

Neuron 552 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.8117. Min Act: -0.0001

Data Index: 331811 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.7675. Min Act: -0.0001

Data Index: 1343104 (C4 (Web Text))

Max Activating Token Index: 438

Text #2

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.7534. Min Act: -0.0001

Data Index: 674793 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.7678. Min Act: -0.0001

Data Index: 267593 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.7886. Min Act: -0.0001

Data Index: 230594 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.7618. Min Act: -0.0001

Data Index: 1014992 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.7500. Min Act: -0.0001

Data Index: 1148288 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.7521. Min Act: -0.0001

Data Index: 1068478 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.7073. Min Act: -0.0001

Data Index: 761352 (C4 (Web Text))

Max Activating Token Index: 281

Text #9

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.7224. Min Act: -0.0001

Data Index: 625135 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.7215. Min Act: -0.0001

Data Index: 546672 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.6965. Min Act: -0.0001

Data Index: 569686 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.6917. Min Act: -0.0001

Data Index: 683351 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.6799. Min Act: -0.0001

Data Index: 494613 (C4 (Web Text))

Max Activating Token Index: 716

Text #14

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.7066. Min Act: -0.0001

Data Index: 471850 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.6896. Min Act: -0.0001

Data Index: 400876 (C4 (Web Text))

Max Activating Token Index: 787

Text #16

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.7552. Min Act: -0.0001

Data Index: 96618 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.6732. Min Act: -0.0001

Data Index: 1390291 (Python Code)

Max Activating Token Index: 835

Text #18

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.6780. Min Act: -0.0001

Data Index: 1231614 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 0.8117. Min Range: -0.8117

Max Act: 0.7160. Min Act: -0.0001

Data Index: 335369 (C4 (Web Text))

Max Activating Token Index: 421