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

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

Neuron 2326 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3627. Min Range: -3.3627

Max Act: 3.3627. Min Act: -0.0001

Data Index: 231602 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 3.3627. Min Range: -3.3627

Max Act: 3.0747. Min Act: -0.0001

Data Index: 200340 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 3.3627. Min Range: -3.3627

Max Act: 2.8598. Min Act: -0.0001

Data Index: 1166857 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 3.3627. Min Range: -3.3627

Max Act: 2.7285. Min Act: -0.0001

Data Index: 918294 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 3.3627. Min Range: -3.3627

Max Act: 2.5737. Min Act: -0.0001

Data Index: 1654 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 3.3627. Min Range: -3.3627

Max Act: 2.6870. Min Act: -0.0001

Data Index: 1166669 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 3.3627. Min Range: -3.3627

Max Act: 2.7907. Min Act: -0.0001

Data Index: 1313881 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 3.3627. Min Range: -3.3627

Max Act: 2.6221. Min Act: -0.0001

Data Index: 645265 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 3.3627. Min Range: -3.3627

Max Act: 2.6031. Min Act: -0.0001

Data Index: 64522 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 3.3627. Min Range: -3.3627

Max Act: 2.6027. Min Act: -0.0001

Data Index: 29095 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 3.3627. Min Range: -3.3627

Max Act: 2.4669. Min Act: -0.0001

Data Index: 586530 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 3.3627. Min Range: -3.3627

Max Act: 2.5557. Min Act: -0.0001

Data Index: 1182466 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 3.3627. Min Range: -3.3627

Max Act: 2.5445. Min Act: -0.0001

Data Index: 360005 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 3.3627. Min Range: -3.3627

Max Act: 2.5441. Min Act: -0.0001

Data Index: 556958 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 3.3627. Min Range: -3.3627

Max Act: 2.5198. Min Act: -0.0001

Data Index: 428789 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 3.3627. Min Range: -3.3627

Max Act: 2.4406. Min Act: -0.0001

Data Index: 726588 (C4 (Web Text))

Max Activating Token Index: 563

Text #16

Max Range: 3.3627. Min Range: -3.3627

Max Act: 2.5634. Min Act: -0.0001

Data Index: 737701 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 3.3627. Min Range: -3.3627

Max Act: 2.3096. Min Act: -0.0001

Data Index: 408115 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 3.3627. Min Range: -3.3627

Max Act: 2.5530. Min Act: -0.0001

Data Index: 885935 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 3.3627. Min Range: -3.3627

Max Act: 2.4091. Min Act: -0.0001

Data Index: 316098 (C4 (Web Text))

Max Activating Token Index: 95