Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2112 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7810. Min Act: -0.0000

Data Index: 222248 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7244. Min Act: -0.0000

Data Index: 404257 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7020. Min Act: -0.0000

Data Index: 396111 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6900. Min Act: -0.0000

Data Index: 80571 (C4 (Web Text))

Max Activating Token Index: 514

Text #4

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6680. Min Act: -0.0000

Data Index: 1231255 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6917. Min Act: -0.0000

Data Index: 412045 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.7090. Min Act: -0.0000

Data Index: 541980 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6704. Min Act: -0.0000

Data Index: 1117785 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6786. Min Act: -0.0000

Data Index: 822492 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6469. Min Act: -0.0000

Data Index: 315759 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6694. Min Act: -0.0000

Data Index: 661170 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6380. Min Act: -0.0000

Data Index: 538779 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6457. Min Act: -0.0000

Data Index: 497685 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6251. Min Act: -0.0000

Data Index: 1166929 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6271. Min Act: -0.0000

Data Index: 934077 (C4 (Web Text))

Max Activating Token Index: 446

Text #15

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6226. Min Act: -0.0000

Data Index: 971570 (C4 (Web Text))

Max Activating Token Index: 724

Text #16

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6224. Min Act: -0.0000

Data Index: 453954 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6145. Min Act: -0.0000

Data Index: 1225380 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6176. Min Act: -0.0000

Data Index: 877998 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 0.7810. Min Range: -0.7810

Max Act: 0.6042. Min Act: -0.0000

Data Index: 947860 (C4 (Web Text))

Max Activating Token Index: 110