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

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

Neuron 2102 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0397. Min Range: -1.0397

Max Act: 1.0397. Min Act: -0.0001

Data Index: 1334995 (C4 (Web Text))

Max Activating Token Index: 878

Text #1

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.8894. Min Act: -0.0001

Data Index: 975791 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.7920. Min Act: -0.0001

Data Index: 444074 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.8034. Min Act: -0.0001

Data Index: 684231 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.7732. Min Act: -0.0001

Data Index: 1258939 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.7711. Min Act: -0.0001

Data Index: 1325323 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.7247. Min Act: -0.0001

Data Index: 944621 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.7020. Min Act: -0.0001

Data Index: 859611 (C4 (Web Text))

Max Activating Token Index: 345

Text #8

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.7600. Min Act: -0.0001

Data Index: 471222 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.7748. Min Act: -0.0001

Data Index: 808197 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.7504. Min Act: -0.0001

Data Index: 1031337 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.7940. Min Act: -0.0001

Data Index: 848465 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.7436. Min Act: -0.0001

Data Index: 734587 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.6757. Min Act: -0.0001

Data Index: 925935 (C4 (Web Text))

Max Activating Token Index: 863

Text #14

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.6957. Min Act: -0.0001

Data Index: 1287519 (C4 (Web Text))

Max Activating Token Index: 992

Text #15

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.7419. Min Act: -0.0001

Data Index: 672827 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.7129. Min Act: -0.0001

Data Index: 249348 (C4 (Web Text))

Max Activating Token Index: 381

Text #17

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.7549. Min Act: -0.0001

Data Index: 785922 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.7324. Min Act: -0.0001

Data Index: 1202828 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 1.0397. Min Range: -1.0397

Max Act: 0.6796. Min Act: -0.0001

Data Index: 79887 (C4 (Web Text))

Max Activating Token Index: 95