Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1942 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.6409. Min Range: -4.6409

Max Act: 4.6409. Min Act: -0.0000

Data Index: 888869 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 4.6409. Min Range: -4.6409

Max Act: 4.2972. Min Act: -0.0000

Data Index: 1151435 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 4.6409. Min Range: -4.6409

Max Act: 3.9613. Min Act: -0.0000

Data Index: 867512 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 4.6409. Min Range: -4.6409

Max Act: 3.9458. Min Act: -0.0000

Data Index: 1036467 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 4.6409. Min Range: -4.6409

Max Act: 3.9172. Min Act: -0.0000

Data Index: 164727 (C4 (Web Text))

Max Activating Token Index: 489

Text #5

Max Range: 4.6409. Min Range: -4.6409

Max Act: 3.8955. Min Act: -0.0000

Data Index: 730109 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 4.6409. Min Range: -4.6409

Max Act: 3.8003. Min Act: -0.0000

Data Index: 268938 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 4.6409. Min Range: -4.6409

Max Act: 3.7819. Min Act: -0.0000

Data Index: 146145 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 4.6409. Min Range: -4.6409

Max Act: 3.7306. Min Act: -0.0000

Data Index: 1206196 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 4.6409. Min Range: -4.6409

Max Act: 3.7253. Min Act: -0.0000

Data Index: 616318 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 4.6409. Min Range: -4.6409

Max Act: 3.6960. Min Act: -0.0000

Data Index: 1089051 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 4.6409. Min Range: -4.6409

Max Act: 3.7718. Min Act: -0.0000

Data Index: 494360 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 4.6409. Min Range: -4.6409

Max Act: 3.9257. Min Act: -0.0000

Data Index: 376871 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 4.6409. Min Range: -4.6409

Max Act: 3.5545. Min Act: -0.0000

Data Index: 527776 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 4.6409. Min Range: -4.6409

Max Act: 3.6247. Min Act: -0.0000

Data Index: 217026 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 4.6409. Min Range: -4.6409

Max Act: 3.4282. Min Act: -0.0000

Data Index: 369289 (C4 (Web Text))

Max Activating Token Index: 836

Text #16

Max Range: 4.6409. Min Range: -4.6409

Max Act: 3.5466. Min Act: -0.0000

Data Index: 414707 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 4.6409. Min Range: -4.6409

Max Act: 3.3798. Min Act: -0.0000

Data Index: 673325 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 4.6409. Min Range: -4.6409

Max Act: 3.1533. Min Act: -0.0000

Data Index: 709427 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 4.6409. Min Range: -4.6409

Max Act: 3.4824. Min Act: -0.0000

Data Index: 1019976 (C4 (Web Text))

Max Activating Token Index: 333