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

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

Neuron 2839 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2527. Min Range: -2.2527

Max Act: 2.2527. Min Act: -0.0000

Data Index: 126664 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 2.2527. Min Range: -2.2527

Max Act: 1.6694. Min Act: -0.0000

Data Index: 180863 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 2.2527. Min Range: -2.2527

Max Act: 1.4741. Min Act: -0.0001

Data Index: 47718 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 2.2527. Min Range: -2.2527

Max Act: 1.5109. Min Act: -0.0000

Data Index: 1224737 (C4 (Web Text))

Max Activating Token Index: 279

Text #4

Max Range: 2.2527. Min Range: -2.2527

Max Act: 1.4734. Min Act: -0.0000

Data Index: 565848 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 2.2527. Min Range: -2.2527

Max Act: 1.3901. Min Act: -0.0000

Data Index: 754154 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 2.2527. Min Range: -2.2527

Max Act: 1.3318. Min Act: -0.0001

Data Index: 1036233 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 2.2527. Min Range: -2.2527

Max Act: 1.3608. Min Act: -0.0000

Data Index: 858808 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 2.2527. Min Range: -2.2527

Max Act: 1.3151. Min Act: -0.0000

Data Index: 645019 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 2.2527. Min Range: -2.2527

Max Act: 1.2218. Min Act: -0.0000

Data Index: 601875 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 2.2527. Min Range: -2.2527

Max Act: 1.3691. Min Act: -0.0000

Data Index: 453606 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 2.2527. Min Range: -2.2527

Max Act: 1.3190. Min Act: -0.0000

Data Index: 1139920 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 2.2527. Min Range: -2.2527

Max Act: 1.3141. Min Act: -0.0000

Data Index: 639296 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 2.2527. Min Range: -2.2527

Max Act: 1.2799. Min Act: -0.0001

Data Index: 1095981 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 2.2527. Min Range: -2.2527

Max Act: 1.3224. Min Act: -0.0000

Data Index: 281265 (C4 (Web Text))

Max Activating Token Index: 770

Text #15

Max Range: 2.2527. Min Range: -2.2527

Max Act: 1.3095. Min Act: -0.0000

Data Index: 508939 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 2.2527. Min Range: -2.2527

Max Act: 1.2354. Min Act: -0.0001

Data Index: 1124975 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 2.2527. Min Range: -2.2527

Max Act: 1.2230. Min Act: -0.0000

Data Index: 716464 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 2.2527. Min Range: -2.2527

Max Act: 1.1847. Min Act: -0.0000

Data Index: 1171107 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 2.2527. Min Range: -2.2527

Max Act: 1.1588. Min Act: -0.0001

Data Index: 1002346 (C4 (Web Text))

Max Activating Token Index: 771