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

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

Neuron 758 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0579. Min Act: -0.0000

Data Index: 542280 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0541. Min Act: -0.0001

Data Index: 1730 (C4 (Web Text))

Max Activating Token Index: 109

Text #2

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0569. Min Act: -0.0001

Data Index: 476971 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0540. Min Act: -0.0001

Data Index: 794039 (C4 (Web Text))

Max Activating Token Index: 489

Text #4

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0527. Min Act: -0.0000

Data Index: 999575 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0525. Min Act: -0.0000

Data Index: 441992 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0538. Min Act: -0.0001

Data Index: 405535 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0541. Min Act: -0.0001

Data Index: 1255824 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0514. Min Act: -0.0000

Data Index: 1359132 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0519. Min Act: -0.0001

Data Index: 691967 (C4 (Web Text))

Max Activating Token Index: 1019

Text #10

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0514. Min Act: -0.0001

Data Index: 105701 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0498. Min Act: -0.0001

Data Index: 1012446 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0530. Min Act: -0.0001

Data Index: 1440765 (Python Code)

Max Activating Token Index: 975

Text #13

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0504. Min Act: -0.0000

Data Index: 169192 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0487. Min Act: -0.0001

Data Index: 896479 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0479. Min Act: -0.0001

Data Index: 982344 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0481. Min Act: -0.0001

Data Index: 1054170 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0459. Min Act: -0.0001

Data Index: 502362 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0433. Min Act: -0.0001

Data Index: 485214 (C4 (Web Text))

Max Activating Token Index: 963

Text #19

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0496. Min Act: -0.0001

Data Index: 270682 (C4 (Web Text))

Max Activating Token Index: 189