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

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

Neuron 2137 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.4452. Min Act: -0.0001

Data Index: 623396 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3709. Min Act: -0.0001

Data Index: 1204667 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3652. Min Act: -0.0001

Data Index: 1082449 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3477. Min Act: -0.0001

Data Index: 1203207 (C4 (Web Text))

Max Activating Token Index: 413

Text #4

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3466. Min Act: -0.0001

Data Index: 184884 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3462. Min Act: -0.0001

Data Index: 395770 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3324. Min Act: -0.0001

Data Index: 827839 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3335. Min Act: -0.0001

Data Index: 821110 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3250. Min Act: -0.0001

Data Index: 102511 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3164. Min Act: -0.0001

Data Index: 893756 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3257. Min Act: -0.0001

Data Index: 898666 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3258. Min Act: -0.0001

Data Index: 1228617 (C4 (Web Text))

Max Activating Token Index: 192

Text #12

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3134. Min Act: -0.0001

Data Index: 200926 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3240. Min Act: -0.0001

Data Index: 751779 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3301. Min Act: -0.0001

Data Index: 519092 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3175. Min Act: -0.0001

Data Index: 1053907 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3174. Min Act: -0.0001

Data Index: 807252 (C4 (Web Text))

Max Activating Token Index: 1002

Text #17

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3175. Min Act: -0.0001

Data Index: 594965 (C4 (Web Text))

Max Activating Token Index: 533

Text #18

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3179. Min Act: -0.0001

Data Index: 699484 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 0.4452. Min Range: -0.4452

Max Act: 0.3055. Min Act: -0.0001

Data Index: 956547 (C4 (Web Text))

Max Activating Token Index: 851