Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2131 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0309. Min Act: -0.0004

Data Index: 828359 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0272. Min Act: -0.0004

Data Index: 957550 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0271. Min Act: -0.0004

Data Index: 783800 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0274. Min Act: -0.0004

Data Index: 981428 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0288. Min Act: -0.0004

Data Index: 259813 (C4 (Web Text))

Max Activating Token Index: 615

Text #5

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0258. Min Act: -0.0004

Data Index: 1265095 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0269. Min Act: -0.0004

Data Index: 1176443 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0248. Min Act: -0.0004

Data Index: 425847 (C4 (Web Text))

Max Activating Token Index: 685

Text #8

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0250. Min Act: -0.0004

Data Index: 284592 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0240. Min Act: -0.0004

Data Index: 1001791 (C4 (Web Text))

Max Activating Token Index: 1021

Text #10

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0248. Min Act: -0.0004

Data Index: 814053 (C4 (Web Text))

Max Activating Token Index: 1021

Text #11

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0250. Min Act: -0.0004

Data Index: 52385 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0233. Min Act: -0.0004

Data Index: 1131997 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0240. Min Act: -0.0004

Data Index: 313741 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0259. Min Act: -0.0004

Data Index: 410935 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0255. Min Act: -0.0004

Data Index: 1340620 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0246. Min Act: -0.0004

Data Index: 481282 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0251. Min Act: -0.0004

Data Index: 346270 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0229. Min Act: -0.0004

Data Index: 817056 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0270. Min Act: -0.0004

Data Index: 19099 (C4 (Web Text))

Max Activating Token Index: 393