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

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

Neuron 3428 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.7735. Min Act: -0.0000

Data Index: 352123 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.6311. Min Act: -0.0000

Data Index: 432991 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.6210. Min Act: -0.0000

Data Index: 64483 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5182. Min Act: -0.0000

Data Index: 89923 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4942. Min Act: -0.0001

Data Index: 1357728 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.5017. Min Act: -0.0000

Data Index: 1136563 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4810. Min Act: -0.0000

Data Index: 958599 (C4 (Web Text))

Max Activating Token Index: 716

Text #7

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4865. Min Act: -0.0000

Data Index: 57124 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4705. Min Act: -0.0000

Data Index: 1188570 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4964. Min Act: -0.0001

Data Index: 1292573 (C4 (Web Text))

Max Activating Token Index: 749

Text #10

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4582. Min Act: -0.0000

Data Index: 659194 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4679. Min Act: -0.0001

Data Index: 1277041 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4242. Min Act: -0.0000

Data Index: 737429 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4657. Min Act: -0.0001

Data Index: 1129319 (C4 (Web Text))

Max Activating Token Index: 914

Text #14

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4275. Min Act: -0.0000

Data Index: 794202 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4360. Min Act: -0.0000

Data Index: 615765 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4432. Min Act: -0.0000

Data Index: 598518 (C4 (Web Text))

Max Activating Token Index: 387

Text #17

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4283. Min Act: -0.0000

Data Index: 143151 (C4 (Web Text))

Max Activating Token Index: 577

Text #18

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4165. Min Act: -0.0001

Data Index: 787793 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 0.7735. Min Range: -0.7735

Max Act: 0.4259. Min Act: -0.0001

Data Index: 616556 (C4 (Web Text))

Max Activating Token Index: 967