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

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

Neuron 3827 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: 0.0504. Min Range: -0.0504

Max Act: 0.0504. Min Act: -0.0003

Data Index: 983658 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0447. Min Act: -0.0003

Data Index: 455605 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0444. Min Act: -0.0003

Data Index: 840952 (C4 (Web Text))

Max Activating Token Index: 284

Text #3

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0421. Min Act: -0.0003

Data Index: 1408347 (Python Code)

Max Activating Token Index: 294

Text #4

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0457. Min Act: -0.0003

Data Index: 526878 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0433. Min Act: -0.0003

Data Index: 1641939 (Python Code)

Max Activating Token Index: 201

Text #6

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0452. Min Act: -0.0003

Data Index: 989762 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0451. Min Act: -0.0003

Data Index: 1117325 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0413. Min Act: -0.0003

Data Index: 491742 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0409. Min Act: -0.0003

Data Index: 1639516 (Python Code)

Max Activating Token Index: 255

Text #10

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0410. Min Act: -0.0003

Data Index: 1373923 (Python Code)

Max Activating Token Index: 258

Text #11

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0423. Min Act: -0.0003

Data Index: 367806 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0424. Min Act: -0.0003

Data Index: 1558324 (Python Code)

Max Activating Token Index: 262

Text #13

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0435. Min Act: -0.0003

Data Index: 1595892 (Python Code)

Max Activating Token Index: 419

Text #14

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0423. Min Act: -0.0003

Data Index: 114078 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0415. Min Act: -0.0003

Data Index: 1580947 (Python Code)

Max Activating Token Index: 109

Text #16

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0415. Min Act: -0.0003

Data Index: 1423635 (Python Code)

Max Activating Token Index: 312

Text #17

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0410. Min Act: -0.0003

Data Index: 1118886 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0393. Min Act: -0.0003

Data Index: 165326 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 0.0504. Min Range: -0.0504

Max Act: 0.0407. Min Act: -0.0003

Data Index: 1445840 (Python Code)

Max Activating Token Index: 312