Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4006 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.5343. Min Act: -0.0001

Data Index: 292538 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.5154. Min Act: -0.0001

Data Index: 935608 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.5471. Min Act: -0.0001

Data Index: 218512 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.4329. Min Act: -0.0001

Data Index: 863915 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.5072. Min Act: -0.0001

Data Index: 1209407 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.3812. Min Act: -0.0001

Data Index: 1081268 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.4626. Min Act: -0.0001

Data Index: 444686 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.3671. Min Act: -0.0001

Data Index: 1043286 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.3493. Min Act: -0.0001

Data Index: 947917 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.4100. Min Act: -0.0001

Data Index: 986993 (C4 (Web Text))

Max Activating Token Index: 637

Text #10

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.3779. Min Act: -0.0001

Data Index: 849094 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.2805. Min Act: -0.0001

Data Index: 1350849 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.2813. Min Act: -0.0001

Data Index: 995758 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.3163. Min Act: -0.0001

Data Index: 966573 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.3141. Min Act: -0.0001

Data Index: 415484 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.3629. Min Act: -0.0001

Data Index: 1233483 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.3476. Min Act: -0.0001

Data Index: 550745 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.3039. Min Act: -0.0001

Data Index: 1062303 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.2555. Min Act: -0.0001

Data Index: 555278 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 1.5471. Min Range: -1.5471

Max Act: 1.3208. Min Act: -0.0001

Data Index: 836788 (C4 (Web Text))

Max Activating Token Index: 981