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

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

Neuron 2382 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: 0.3172. Min Range: -0.3172

Max Act: 0.3172. Min Act: -0.0001

Data Index: 647078 (C4 (Web Text))

Max Activating Token Index: 555

Text #1

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.3157. Min Act: -0.0001

Data Index: 922372 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2847. Min Act: -0.0001

Data Index: 571722 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2693. Min Act: -0.0001

Data Index: 1287714 (C4 (Web Text))

Max Activating Token Index: 850

Text #4

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2679. Min Act: -0.0001

Data Index: 976803 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2713. Min Act: -0.0001

Data Index: 1224328 (C4 (Web Text))

Max Activating Token Index: 718

Text #6

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2709. Min Act: -0.0001

Data Index: 346291 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2428. Min Act: -0.0001

Data Index: 1139255 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2647. Min Act: -0.0001

Data Index: 1033104 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2641. Min Act: -0.0001

Data Index: 760839 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2634. Min Act: -0.0001

Data Index: 1129385 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2628. Min Act: -0.0001

Data Index: 697120 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2598. Min Act: -0.0001

Data Index: 340276 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2588. Min Act: -0.0001

Data Index: 197313 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2526. Min Act: -0.0001

Data Index: 42339 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2485. Min Act: -0.0001

Data Index: 374266 (C4 (Web Text))

Max Activating Token Index: 876

Text #16

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2597. Min Act: -0.0001

Data Index: 689953 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2328. Min Act: -0.0001

Data Index: 756061 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2244. Min Act: -0.0001

Data Index: 34305 (C4 (Web Text))

Max Activating Token Index: 360

Text #19

Max Range: 0.3172. Min Range: -0.3172

Max Act: 0.2261. Min Act: -0.0001

Data Index: 547075 (C4 (Web Text))

Max Activating Token Index: 807