Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3596 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.6052. Min Act: -0.0000

Data Index: 608134 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5928. Min Act: -0.0000

Data Index: 477315 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.6551. Min Act: -0.0000

Data Index: 795561 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.6050. Min Act: -0.0000

Data Index: 1299971 (C4 (Web Text))

Max Activating Token Index: 92

Text #4

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5649. Min Act: -0.0000

Data Index: 715508 (C4 (Web Text))

Max Activating Token Index: 154

Text #5

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5789. Min Act: -0.0000

Data Index: 638460 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5587. Min Act: -0.0000

Data Index: 818811 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5729. Min Act: -0.0000

Data Index: 488782 (C4 (Web Text))

Max Activating Token Index: 92

Text #8

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5710. Min Act: -0.0000

Data Index: 669266 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5704. Min Act: -0.0000

Data Index: 1115724 (C4 (Web Text))

Max Activating Token Index: 668

Text #10

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5648. Min Act: -0.0000

Data Index: 832016 (C4 (Web Text))

Max Activating Token Index: 572

Text #11

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5784. Min Act: -0.0000

Data Index: 63434 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5444. Min Act: -0.0000

Data Index: 197274 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5537. Min Act: -0.0000

Data Index: 653707 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5028. Min Act: -0.0000

Data Index: 649172 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5243. Min Act: -0.0000

Data Index: 877973 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.4977. Min Act: -0.0000

Data Index: 254180 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5579. Min Act: -0.0000

Data Index: 467413 (C4 (Web Text))

Max Activating Token Index: 805

Text #18

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5253. Min Act: -0.0000

Data Index: 301740 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 0.6551. Min Range: -0.6551

Max Act: 0.5153. Min Act: -0.0000

Data Index: 142720 (C4 (Web Text))

Max Activating Token Index: 40