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

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

Neuron 3974 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4133. Min Range: -2.4133

Max Act: 2.4133. Min Act: -0.0000

Data Index: 418457 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 2.4133. Min Range: -2.4133

Max Act: 2.4024. Min Act: -0.0000

Data Index: 1137180 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 2.4133. Min Range: -2.4133

Max Act: 2.2138. Min Act: -0.0000

Data Index: 791379 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 2.4133. Min Range: -2.4133

Max Act: 2.1572. Min Act: -0.0000

Data Index: 1044814 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 2.4133. Min Range: -2.4133

Max Act: 1.9309. Min Act: -0.0000

Data Index: 1173576 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 2.4133. Min Range: -2.4133

Max Act: 2.0418. Min Act: -0.0000

Data Index: 315675 (C4 (Web Text))

Max Activating Token Index: 1013

Text #6

Max Range: 2.4133. Min Range: -2.4133

Max Act: 1.9931. Min Act: -0.0000

Data Index: 359944 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 2.4133. Min Range: -2.4133

Max Act: 1.8550. Min Act: -0.0000

Data Index: 458083 (C4 (Web Text))

Max Activating Token Index: 466

Text #8

Max Range: 2.4133. Min Range: -2.4133

Max Act: 1.8867. Min Act: -0.0000

Data Index: 1167029 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 2.4133. Min Range: -2.4133

Max Act: 1.8632. Min Act: 0.0000

Data Index: 26399 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 2.4133. Min Range: -2.4133

Max Act: 1.8448. Min Act: -0.0000

Data Index: 472128 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 2.4133. Min Range: -2.4133

Max Act: 1.9182. Min Act: -0.0000

Data Index: 403739 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 2.4133. Min Range: -2.4133

Max Act: 1.7546. Min Act: -0.0000

Data Index: 293634 (C4 (Web Text))

Max Activating Token Index: 391

Text #13

Max Range: 2.4133. Min Range: -2.4133

Max Act: 1.7479. Min Act: -0.0000

Data Index: 370176 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 2.4133. Min Range: -2.4133

Max Act: 1.7458. Min Act: -0.0000

Data Index: 680112 (C4 (Web Text))

Max Activating Token Index: 197

Text #15

Max Range: 2.4133. Min Range: -2.4133

Max Act: 1.8417. Min Act: -0.0000

Data Index: 176852 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 2.4133. Min Range: -2.4133

Max Act: 1.6332. Min Act: -0.0000

Data Index: 1006819 (C4 (Web Text))

Max Activating Token Index: 1015

Text #17

Max Range: 2.4133. Min Range: -2.4133

Max Act: 1.7103. Min Act: -0.0000

Data Index: 1326852 (C4 (Web Text))

Max Activating Token Index: 901

Text #18

Max Range: 2.4133. Min Range: -2.4133

Max Act: 1.7998. Min Act: -0.0000

Data Index: 391594 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 2.4133. Min Range: -2.4133

Max Act: 1.6857. Min Act: -0.0000

Data Index: 592674 (C4 (Web Text))

Max Activating Token Index: 109