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

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

Neuron 585 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0591. Min Act: -0.0001

Data Index: 404266 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0410. Min Act: -0.0001

Data Index: 118370 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0415. Min Act: -0.0001

Data Index: 409622 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0396. Min Act: -0.0001

Data Index: 1564819 (Python Code)

Max Activating Token Index: 250

Text #4

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0408. Min Act: -0.0001

Data Index: 193145 (C4 (Web Text))

Max Activating Token Index: 238

Text #5

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0397. Min Act: -0.0000

Data Index: 1306377 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0380. Min Act: -0.0000

Data Index: 1425877 (Python Code)

Max Activating Token Index: 460

Text #7

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0370. Min Act: -0.0000

Data Index: 443107 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0345. Min Act: -0.0001

Data Index: 238078 (C4 (Web Text))

Max Activating Token Index: 853

Text #9

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0382. Min Act: -0.0001

Data Index: 1140341 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0358. Min Act: -0.0000

Data Index: 186089 (C4 (Web Text))

Max Activating Token Index: 518

Text #11

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0370. Min Act: -0.0001

Data Index: 526242 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0365. Min Act: -0.0000

Data Index: 989152 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0411. Min Act: -0.0001

Data Index: 1309549 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0356. Min Act: -0.0000

Data Index: 923916 (C4 (Web Text))

Max Activating Token Index: 847

Text #15

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0335. Min Act: -0.0001

Data Index: 123007 (C4 (Web Text))

Max Activating Token Index: 168

Text #16

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0333. Min Act: -0.0001

Data Index: 380272 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0337. Min Act: -0.0001

Data Index: 1588618 (Python Code)

Max Activating Token Index: 66

Text #18

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0330. Min Act: -0.0000

Data Index: 872812 (C4 (Web Text))

Max Activating Token Index: 978

Text #19

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0328. Min Act: -0.0000

Data Index: 1256133 (C4 (Web Text))

Max Activating Token Index: 122