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

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

Neuron 3 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: 0.0483. Min Range: -0.0483

Max Act: 0.0449. Min Act: -0.0004

Data Index: 687698 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0483. Min Act: -0.0004

Data Index: 573471 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0464. Min Act: -0.0004

Data Index: 1525591 (Python Code)

Max Activating Token Index: 74

Text #3

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0480. Min Act: -0.0004

Data Index: 1357257 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0481. Min Act: -0.0004

Data Index: 698555 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0439. Min Act: -0.0004

Data Index: 294982 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0477. Min Act: -0.0004

Data Index: 1466279 (Python Code)

Max Activating Token Index: 428

Text #7

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0437. Min Act: -0.0004

Data Index: 1474570 (Python Code)

Max Activating Token Index: 166

Text #8

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0435. Min Act: -0.0004

Data Index: 1594329 (Python Code)

Max Activating Token Index: 210

Text #9

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0435. Min Act: -0.0004

Data Index: 1540423 (Python Code)

Max Activating Token Index: 303

Text #10

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0430. Min Act: -0.0004

Data Index: 1499185 (Python Code)

Max Activating Token Index: 426

Text #11

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0433. Min Act: -0.0004

Data Index: 1528401 (Python Code)

Max Activating Token Index: 174

Text #12

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0446. Min Act: -0.0004

Data Index: 513960 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0464. Min Act: -0.0004

Data Index: 319946 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0415. Min Act: -0.0004

Data Index: 1622140 (Python Code)

Max Activating Token Index: 206

Text #15

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0413. Min Act: -0.0004

Data Index: 1447489 (Python Code)

Max Activating Token Index: 444

Text #16

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0429. Min Act: -0.0004

Data Index: 434244 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0465. Min Act: -0.0004

Data Index: 306360 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0408. Min Act: -0.0004

Data Index: 114902 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 0.0483. Min Range: -0.0483

Max Act: 0.0437. Min Act: -0.0004

Data Index: 1540435 (Python Code)

Max Activating Token Index: 826