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

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

Neuron 869 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8124. Min Range: -1.8124

Max Act: 1.8124. Min Act: -0.0002

Data Index: 598388 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 1.8124. Min Range: -1.8124

Max Act: 1.7001. Min Act: -0.0002

Data Index: 739816 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 1.8124. Min Range: -1.8124

Max Act: 1.6035. Min Act: -0.0002

Data Index: 852689 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 1.8124. Min Range: -1.8124

Max Act: 1.6076. Min Act: -0.0002

Data Index: 623126 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 1.8124. Min Range: -1.8124

Max Act: 1.5820. Min Act: -0.0002

Data Index: 1299500 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 1.8124. Min Range: -1.8124

Max Act: 1.5543. Min Act: -0.0001

Data Index: 201290 (C4 (Web Text))

Max Activating Token Index: 14

Text #6

Max Range: 1.8124. Min Range: -1.8124

Max Act: 1.5579. Min Act: -0.0002

Data Index: 17696 (C4 (Web Text))

Max Activating Token Index: 2

Text #7

Max Range: 1.8124. Min Range: -1.8124

Max Act: 1.5718. Min Act: -0.0002

Data Index: 122095 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 1.8124. Min Range: -1.8124

Max Act: 1.5595. Min Act: -0.0002

Data Index: 341904 (C4 (Web Text))

Max Activating Token Index: 36

Text #9

Max Range: 1.8124. Min Range: -1.8124

Max Act: 1.5369. Min Act: -0.0002

Data Index: 23609 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 1.8124. Min Range: -1.8124

Max Act: 1.4973. Min Act: -0.0002

Data Index: 1151998 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 1.8124. Min Range: -1.8124

Max Act: 1.4900. Min Act: -0.0001

Data Index: 398004 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 1.8124. Min Range: -1.8124

Max Act: 1.4821. Min Act: -0.0001

Data Index: 306802 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 1.8124. Min Range: -1.8124

Max Act: 1.4683. Min Act: -0.0001

Data Index: 1094108 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 1.8124. Min Range: -1.8124

Max Act: 1.5118. Min Act: -0.0002

Data Index: 1163924 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 1.8124. Min Range: -1.8124

Max Act: 1.4223. Min Act: -0.0002

Data Index: 835764 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 1.8124. Min Range: -1.8124

Max Act: 1.4480. Min Act: -0.0002

Data Index: 977174 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 1.8124. Min Range: -1.8124

Max Act: 1.4816. Min Act: -0.0001

Data Index: 1198401 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 1.8124. Min Range: -1.8124

Max Act: 1.4307. Min Act: -0.0002

Data Index: 1204899 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 1.8124. Min Range: -1.8124

Max Act: 1.4227. Min Act: -0.0002

Data Index: 476969 (C4 (Web Text))

Max Activating Token Index: 240