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

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

Neuron 1046 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: 0.2875. Min Range: -0.2875

Max Act: 0.2875. Min Act: -0.0000

Data Index: 706390 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2704. Min Act: -0.0000

Data Index: 970486 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2528. Min Act: -0.0000

Data Index: 828542 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2477. Min Act: -0.0000

Data Index: 245462 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2470. Min Act: -0.0000

Data Index: 608560 (C4 (Web Text))

Max Activating Token Index: 728

Text #5

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2382. Min Act: -0.0000

Data Index: 174035 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2236. Min Act: -0.0000

Data Index: 98936 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2225. Min Act: -0.0000

Data Index: 29903 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2235. Min Act: -0.0000

Data Index: 91650 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2082. Min Act: -0.0000

Data Index: 137817 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2190. Min Act: -0.0000

Data Index: 31045 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2196. Min Act: -0.0000

Data Index: 1252549 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2194. Min Act: -0.0000

Data Index: 14880 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2186. Min Act: -0.0000

Data Index: 1250828 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2184. Min Act: -0.0000

Data Index: 202767 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2217. Min Act: -0.0000

Data Index: 343409 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2268. Min Act: -0.0000

Data Index: 478582 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2254. Min Act: -0.0000

Data Index: 1041753 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2087. Min Act: -0.0000

Data Index: 442902 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 0.2875. Min Range: -0.2875

Max Act: 0.2161. Min Act: -0.0000

Data Index: 946664 (C4 (Web Text))

Max Activating Token Index: 444