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

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

Neuron 855 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8583. Min Range: -0.8583

Max Act: 0.8583. Min Act: -0.0001

Data Index: 374343 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 0.8583. Min Range: -0.8583

Max Act: 0.8443. Min Act: -0.0001

Data Index: 709466 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 0.8583. Min Range: -0.8583

Max Act: 0.8082. Min Act: -0.0001

Data Index: 798734 (C4 (Web Text))

Max Activating Token Index: 167

Text #3

Max Range: 0.8583. Min Range: -0.8583

Max Act: 0.8039. Min Act: -0.0001

Data Index: 679521 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 0.8583. Min Range: -0.8583

Max Act: 0.7545. Min Act: -0.0001

Data Index: 158897 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 0.8583. Min Range: -0.8583

Max Act: 0.7727. Min Act: -0.0001

Data Index: 139913 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.8583. Min Range: -0.8583

Max Act: 0.7619. Min Act: -0.0001

Data Index: 894769 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 0.8583. Min Range: -0.8583

Max Act: 0.7404. Min Act: -0.0001

Data Index: 723040 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.8583. Min Range: -0.8583

Max Act: 0.7030. Min Act: -0.0001

Data Index: 275619 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 0.8583. Min Range: -0.8583

Max Act: 0.7161. Min Act: -0.0001

Data Index: 868122 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 0.8583. Min Range: -0.8583

Max Act: 0.7156. Min Act: -0.0001

Data Index: 300880 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 0.8583. Min Range: -0.8583

Max Act: 0.7391. Min Act: -0.0001

Data Index: 1259560 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 0.8583. Min Range: -0.8583

Max Act: 0.6912. Min Act: -0.0001

Data Index: 444990 (C4 (Web Text))

Max Activating Token Index: 415

Text #13

Max Range: 0.8583. Min Range: -0.8583

Max Act: 0.6713. Min Act: -0.0001

Data Index: 1579170 (Python Code)

Max Activating Token Index: 143

Text #14

Max Range: 0.8583. Min Range: -0.8583

Max Act: 0.6920. Min Act: -0.0001

Data Index: 1583471 (Python Code)

Max Activating Token Index: 33

Text #15

Max Range: 0.8583. Min Range: -0.8583

Max Act: 0.6827. Min Act: 0.0006

Data Index: 1093277 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 0.8583. Min Range: -0.8583

Max Act: 0.6539. Min Act: -0.0001

Data Index: 851114 (C4 (Web Text))

Max Activating Token Index: 403

Text #17

Max Range: 0.8583. Min Range: -0.8583

Max Act: 0.6711. Min Act: -0.0001

Data Index: 525348 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 0.8583. Min Range: -0.8583

Max Act: 0.6283. Min Act: -0.0001

Data Index: 1583111 (Python Code)

Max Activating Token Index: 87

Text #19

Max Range: 0.8583. Min Range: -0.8583

Max Act: 0.6575. Min Act: -0.0001

Data Index: 362186 (C4 (Web Text))

Max Activating Token Index: 487