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

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

Neuron 2339 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: 0.8880. Min Range: -0.8880

Max Act: 0.8880. Min Act: -0.0001

Data Index: 538949 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.7381. Min Act: -0.0001

Data Index: 351537 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.7589. Min Act: -0.0001

Data Index: 491961 (C4 (Web Text))

Max Activating Token Index: 140

Text #3

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.7884. Min Act: -0.0001

Data Index: 657711 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.7110. Min Act: -0.0001

Data Index: 424140 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.7334. Min Act: -0.0001

Data Index: 1302563 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.6993. Min Act: -0.0001

Data Index: 528155 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.6326. Min Act: -0.0001

Data Index: 525695 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.7121. Min Act: -0.0001

Data Index: 1292157 (C4 (Web Text))

Max Activating Token Index: 587

Text #9

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.7094. Min Act: -0.0001

Data Index: 192089 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.6545. Min Act: -0.0001

Data Index: 158985 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.6621. Min Act: -0.0001

Data Index: 244119 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.6816. Min Act: -0.0001

Data Index: 650034 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.6543. Min Act: -0.0001

Data Index: 661278 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.6299. Min Act: -0.0001

Data Index: 569000 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.6453. Min Act: -0.0001

Data Index: 222262 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.6121. Min Act: -0.0001

Data Index: 143960 (C4 (Web Text))

Max Activating Token Index: 540

Text #17

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.5697. Min Act: -0.0001

Data Index: 998938 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.5831. Min Act: -0.0001

Data Index: 487421 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 0.8880. Min Range: -0.8880

Max Act: 0.5595. Min Act: -0.0001

Data Index: 800895 (C4 (Web Text))

Max Activating Token Index: 592