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

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

Neuron 598 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6525. Min Range: -1.6525

Max Act: 1.6525. Min Act: -0.0000

Data Index: 507749 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 1.6525. Min Range: -1.6525

Max Act: 1.3708. Min Act: -0.0000

Data Index: 583515 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 1.6525. Min Range: -1.6525

Max Act: 1.3532. Min Act: -0.0001

Data Index: 1273378 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 1.6525. Min Range: -1.6525

Max Act: 1.0020. Min Act: -0.0000

Data Index: 486469 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 1.6525. Min Range: -1.6525

Max Act: 0.9981. Min Act: -0.0000

Data Index: 286982 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 1.6525. Min Range: -1.6525

Max Act: 0.9728. Min Act: -0.0000

Data Index: 855450 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 1.6525. Min Range: -1.6525

Max Act: 0.9986. Min Act: -0.0001

Data Index: 546315 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 1.6525. Min Range: -1.6525

Max Act: 0.9693. Min Act: -0.0000

Data Index: 680747 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 1.6525. Min Range: -1.6525

Max Act: 0.9682. Min Act: -0.0000

Data Index: 994577 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 1.6525. Min Range: -1.6525

Max Act: 0.9406. Min Act: -0.0000

Data Index: 1254049 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 1.6525. Min Range: -1.6525

Max Act: 0.8587. Min Act: -0.0000

Data Index: 700654 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 1.6525. Min Range: -1.6525

Max Act: 0.9244. Min Act: -0.0000

Data Index: 4506 (C4 (Web Text))

Max Activating Token Index: 852

Text #12

Max Range: 1.6525. Min Range: -1.6525

Max Act: 0.8519. Min Act: -0.0000

Data Index: 205589 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 1.6525. Min Range: -1.6525

Max Act: 0.8869. Min Act: -0.0001

Data Index: 836453 (C4 (Web Text))

Max Activating Token Index: 560

Text #14

Max Range: 1.6525. Min Range: -1.6525

Max Act: 0.8774. Min Act: -0.0000

Data Index: 1211184 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 1.6525. Min Range: -1.6525

Max Act: 0.8989. Min Act: -0.0000

Data Index: 1257769 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 1.6525. Min Range: -1.6525

Max Act: 0.8598. Min Act: -0.0000

Data Index: 769154 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 1.6525. Min Range: -1.6525

Max Act: 0.8117. Min Act: -0.0000

Data Index: 469427 (C4 (Web Text))

Max Activating Token Index: 903

Text #18

Max Range: 1.6525. Min Range: -1.6525

Max Act: 0.8728. Min Act: -0.0000

Data Index: 638092 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 1.6525. Min Range: -1.6525

Max Act: 0.9056. Min Act: -0.0001

Data Index: 330164 (C4 (Web Text))

Max Activating Token Index: 588