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

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

Neuron 586 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.4897. Min Act: -0.0001

Data Index: 1026169 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.3675. Min Act: -0.0001

Data Index: 261197 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.3001. Min Act: -0.0000

Data Index: 601943 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.2744. Min Act: -0.0000

Data Index: 453782 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.2979. Min Act: -0.0000

Data Index: 221928 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.2921. Min Act: -0.0000

Data Index: 282180 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.3064. Min Act: -0.0000

Data Index: 340422 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.3022. Min Act: -0.0000

Data Index: 578965 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.2897. Min Act: -0.0001

Data Index: 637808 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.2900. Min Act: -0.0001

Data Index: 727427 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.2954. Min Act: -0.0000

Data Index: 511818 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.2698. Min Act: -0.0001

Data Index: 558512 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.2635. Min Act: -0.0000

Data Index: 1160080 (C4 (Web Text))

Max Activating Token Index: 386

Text #13

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.2936. Min Act: -0.0000

Data Index: 365494 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.2697. Min Act: -0.0000

Data Index: 868128 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.2592. Min Act: -0.0000

Data Index: 1247402 (C4 (Web Text))

Max Activating Token Index: 773

Text #16

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.2504. Min Act: -0.0000

Data Index: 486756 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.2860. Min Act: -0.0001

Data Index: 918484 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.2541. Min Act: -0.0001

Data Index: 917212 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 0.4897. Min Range: -0.4897

Max Act: 0.2530. Min Act: -0.0000

Data Index: 986994 (C4 (Web Text))

Max Activating Token Index: 59