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

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

Neuron 5856 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4497. Min Range: -0.4497

Max Act: 0.4497. Min Act: -0.0000

Data Index: 248668 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.4497. Min Range: -0.4497

Max Act: 0.4123. Min Act: -0.0000

Data Index: 1146998 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 0.4497. Min Range: -0.4497

Max Act: 0.3714. Min Act: -0.0000

Data Index: 173906 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 0.4497. Min Range: -0.4497

Max Act: 0.3841. Min Act: -0.0000

Data Index: 625539 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 0.4497. Min Range: -0.4497

Max Act: 0.3518. Min Act: -0.0000

Data Index: 1203708 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.4497. Min Range: -0.4497

Max Act: 0.3322. Min Act: -0.0000

Data Index: 1136042 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 0.4497. Min Range: -0.4497

Max Act: 0.3438. Min Act: -0.0000

Data Index: 294040 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 0.4497. Min Range: -0.4497

Max Act: 0.3401. Min Act: -0.0000

Data Index: 30302 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.4497. Min Range: -0.4497

Max Act: 0.3478. Min Act: -0.0000

Data Index: 1125013 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 0.4497. Min Range: -0.4497

Max Act: 0.3245. Min Act: -0.0000

Data Index: 21332 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 0.4497. Min Range: -0.4497

Max Act: 0.3129. Min Act: -0.0000

Data Index: 811851 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.4497. Min Range: -0.4497

Max Act: 0.3081. Min Act: -0.0000

Data Index: 71794 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.4497. Min Range: -0.4497

Max Act: 0.3153. Min Act: -0.0000

Data Index: 358038 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 0.4497. Min Range: -0.4497

Max Act: 0.3047. Min Act: -0.0000

Data Index: 810169 (C4 (Web Text))

Max Activating Token Index: 854

Text #14

Max Range: 0.4497. Min Range: -0.4497

Max Act: 0.3135. Min Act: -0.0000

Data Index: 433531 (C4 (Web Text))

Max Activating Token Index: 478

Text #15

Max Range: 0.4497. Min Range: -0.4497

Max Act: 0.3090. Min Act: -0.0000

Data Index: 849469 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 0.4497. Min Range: -0.4497

Max Act: 0.3014. Min Act: -0.0000

Data Index: 738480 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 0.4497. Min Range: -0.4497

Max Act: 0.2998. Min Act: -0.0000

Data Index: 1069043 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 0.4497. Min Range: -0.4497

Max Act: 0.3033. Min Act: -0.0000

Data Index: 651670 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 0.4497. Min Range: -0.4497

Max Act: 0.2992. Min Act: -0.0000

Data Index: 1119319 (C4 (Web Text))

Max Activating Token Index: 729