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

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

Neuron 3352 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0456. Min Act: -0.0003

Data Index: 1243538 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0378. Min Act: -0.0003

Data Index: 177010 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0381. Min Act: -0.0003

Data Index: 1230242 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0370. Min Act: -0.0003

Data Index: 1184444 (C4 (Web Text))

Max Activating Token Index: 752

Text #4

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0373. Min Act: -0.0003

Data Index: 729848 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0333. Min Act: -0.0003

Data Index: 1119240 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0344. Min Act: -0.0003

Data Index: 441332 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0342. Min Act: -0.0003

Data Index: 353787 (C4 (Web Text))

Max Activating Token Index: 974

Text #8

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0323. Min Act: -0.0003

Data Index: 1029763 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0281. Min Act: -0.0003

Data Index: 392758 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0310. Min Act: -0.0003

Data Index: 232375 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0311. Min Act: -0.0003

Data Index: 1267065 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0260. Min Act: -0.0003

Data Index: 21340 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0366. Min Act: -0.0003

Data Index: 997900 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0303. Min Act: -0.0003

Data Index: 456405 (C4 (Web Text))

Max Activating Token Index: 1000

Text #15

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1249404 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0309. Min Act: -0.0004

Data Index: 858391 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0280. Min Act: -0.0003

Data Index: 1063943 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0297. Min Act: -0.0003

Data Index: 191702 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0307. Min Act: -0.0003

Data Index: 47570 (C4 (Web Text))

Max Activating Token Index: 372