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

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

Neuron 1508 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.3530. Min Act: -0.0001

Data Index: 1178043 (C4 (Web Text))

Max Activating Token Index: 94

Text #1

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.3542. Min Act: -0.0001

Data Index: 795198 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.3139. Min Act: -0.0001

Data Index: 1094211 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.3135. Min Act: -0.0001

Data Index: 839851 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.3165. Min Act: -0.0000

Data Index: 636355 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.3056. Min Act: -0.0001

Data Index: 1124322 (C4 (Web Text))

Max Activating Token Index: 647

Text #6

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.3180. Min Act: -0.0001

Data Index: 56937 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.3122. Min Act: -0.0001

Data Index: 392220 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.3164. Min Act: -0.0000

Data Index: 1128518 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.3073. Min Act: -0.0001

Data Index: 1266164 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.3237. Min Act: -0.0001

Data Index: 167837 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.2844. Min Act: -0.0001

Data Index: 1042325 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.2963. Min Act: -0.0001

Data Index: 936548 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.2928. Min Act: 0.0000

Data Index: 1020916 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.2826. Min Act: 0.0001

Data Index: 792195 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.2860. Min Act: -0.0001

Data Index: 250800 (C4 (Web Text))

Max Activating Token Index: 421

Text #16

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.2847. Min Act: -0.0000

Data Index: 396091 (C4 (Web Text))

Max Activating Token Index: 643

Text #17

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.2858. Min Act: -0.0001

Data Index: 3211 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.2926. Min Act: -0.0001

Data Index: 118712 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 0.3542. Min Range: -0.3542

Max Act: 0.2852. Min Act: -0.0001

Data Index: 453790 (C4 (Web Text))

Max Activating Token Index: 987