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

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

Neuron 573 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.7674. Min Act: -0.0001

Data Index: 1376907 (Python Code)

Max Activating Token Index: 450

Text #1

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.6253. Min Act: -0.0001

Data Index: 1387014 (Python Code)

Max Activating Token Index: 816

Text #2

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.5424. Min Act: -0.0001

Data Index: 1493435 (Python Code)

Max Activating Token Index: 710

Text #3

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.5519. Min Act: -0.0001

Data Index: 1595330 (Python Code)

Max Activating Token Index: 430

Text #4

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.4997. Min Act: -0.0001

Data Index: 1389960 (Python Code)

Max Activating Token Index: 979

Text #5

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.4143. Min Act: -0.0001

Data Index: 1369714 (Python Code)

Max Activating Token Index: 862

Text #6

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.4373. Min Act: -0.0001

Data Index: 1407568 (Python Code)

Max Activating Token Index: 457

Text #7

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.3692. Min Act: -0.0001

Data Index: 408675 (C4 (Web Text))

Max Activating Token Index: 123

Text #8

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.3243. Min Act: -0.0001

Data Index: 408222 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.3358. Min Act: -0.0001

Data Index: 1580593 (Python Code)

Max Activating Token Index: 367

Text #10

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.3268. Min Act: -0.0001

Data Index: 631250 (C4 (Web Text))

Max Activating Token Index: 375

Text #11

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.4095. Min Act: -0.0001

Data Index: 1522463 (Python Code)

Max Activating Token Index: 368

Text #12

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.3927. Min Act: -0.0001

Data Index: 1444818 (Python Code)

Max Activating Token Index: 501

Text #13

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.3429. Min Act: -0.0001

Data Index: 1558070 (Python Code)

Max Activating Token Index: 57

Text #14

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.2581. Min Act: -0.0001

Data Index: 1543942 (Python Code)

Max Activating Token Index: 540

Text #15

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.3454. Min Act: -0.0001

Data Index: 165459 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.2291. Min Act: -0.0001

Data Index: 1498281 (Python Code)

Max Activating Token Index: 629

Text #17

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.3353. Min Act: -0.0001

Data Index: 1573960 (Python Code)

Max Activating Token Index: 799

Text #18

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.3489. Min Act: -0.0001

Data Index: 1517178 (Python Code)

Max Activating Token Index: 436

Text #19

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.2774. Min Act: -0.0001

Data Index: 1580330 (Python Code)

Max Activating Token Index: 453