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

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

Neuron 431 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.8328. Min Act: -0.0001

Data Index: 603298 (C4 (Web Text))

Max Activating Token Index: 28

Text #1

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.7608. Min Act: -0.0001

Data Index: 105376 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.7596. Min Act: -0.0000

Data Index: 1309112 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.6686. Min Act: -0.0001

Data Index: 585241 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.6323. Min Act: -0.0000

Data Index: 58860 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.5362. Min Act: -0.0001

Data Index: 21879 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.4907. Min Act: -0.0000

Data Index: 215745 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.4989. Min Act: 0.0000

Data Index: 732654 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.4242. Min Act: -0.0000

Data Index: 299372 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.3741. Min Act: -0.0000

Data Index: 130889 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.4185. Min Act: -0.0000

Data Index: 1099911 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.4101. Min Act: -0.0001

Data Index: 1258330 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.3260. Min Act: -0.0001

Data Index: 567276 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.4725. Min Act: -0.0001

Data Index: 823381 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.3902. Min Act: -0.0000

Data Index: 165345 (C4 (Web Text))

Max Activating Token Index: 587

Text #15

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.3516. Min Act: -0.0001

Data Index: 955442 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.3954. Min Act: -0.0001

Data Index: 594516 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.3675. Min Act: 0.0000

Data Index: 642299 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.3248. Min Act: -0.0000

Data Index: 939928 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 1.8328. Min Range: -1.8328

Max Act: 1.3991. Min Act: -0.0000

Data Index: 1272169 (C4 (Web Text))

Max Activating Token Index: 723