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

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

Neuron 618 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: 1.0602. Min Range: -1.0602

Max Act: 1.0102. Min Act: -0.0001

Data Index: 965322 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 1.0602. Min Range: -1.0602

Max Act: 1.0602. Min Act: -0.0001

Data Index: 1345518 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.8941. Min Act: -0.0001

Data Index: 597846 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.8636. Min Act: -0.0001

Data Index: 1128130 (C4 (Web Text))

Max Activating Token Index: 460

Text #4

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.8656. Min Act: -0.0001

Data Index: 165875 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.8262. Min Act: -0.0001

Data Index: 117118 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.8725. Min Act: -0.0001

Data Index: 1313343 (C4 (Web Text))

Max Activating Token Index: 1008

Text #7

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.8444. Min Act: -0.0001

Data Index: 912314 (C4 (Web Text))

Max Activating Token Index: 154

Text #8

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.8399. Min Act: -0.0001

Data Index: 1002346 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.8190. Min Act: -0.0001

Data Index: 1121979 (C4 (Web Text))

Max Activating Token Index: 958

Text #10

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.8039. Min Act: -0.0001

Data Index: 1132351 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.6972. Min Act: -0.0001

Data Index: 369001 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.8049. Min Act: -0.0001

Data Index: 430714 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.7846. Min Act: -0.0001

Data Index: 527535 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.7553. Min Act: -0.0001

Data Index: 526088 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.7579. Min Act: -0.0001

Data Index: 592118 (C4 (Web Text))

Max Activating Token Index: 537

Text #16

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.7904. Min Act: -0.0001

Data Index: 1312311 (C4 (Web Text))

Max Activating Token Index: 945

Text #17

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.7567. Min Act: -0.0001

Data Index: 1015066 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.7477. Min Act: -0.0001

Data Index: 965453 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 1.0602. Min Range: -1.0602

Max Act: 0.7033. Min Act: -0.0001

Data Index: 668720 (C4 (Web Text))

Max Activating Token Index: 422