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

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

Neuron 1137 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: 1.7201. Min Range: -1.7201

Max Act: 1.7201. Min Act: -0.0001

Data Index: 103774 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.7060. Min Act: -0.0001

Data Index: 198198 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.5176. Min Act: -0.0001

Data Index: 134627 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.3926. Min Act: -0.0001

Data Index: 355052 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.4975. Min Act: -0.0001

Data Index: 83997 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.4579. Min Act: -0.0001

Data Index: 1339537 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.2084. Min Act: -0.0001

Data Index: 961424 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.4053. Min Act: -0.0001

Data Index: 768293 (C4 (Web Text))

Max Activating Token Index: 164

Text #8

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.2524. Min Act: -0.0001

Data Index: 157847 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.3684. Min Act: -0.0001

Data Index: 88567 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.1904. Min Act: -0.0001

Data Index: 1204106 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.2192. Min Act: -0.0001

Data Index: 735605 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.2450. Min Act: -0.0001

Data Index: 461335 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.3100. Min Act: -0.0001

Data Index: 112358 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.3568. Min Act: -0.0001

Data Index: 804097 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.3033. Min Act: -0.0001

Data Index: 915019 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.2181. Min Act: -0.0001

Data Index: 580710 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.1652. Min Act: -0.0001

Data Index: 416567 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.2122. Min Act: -0.0001

Data Index: 1018685 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.0030. Min Act: -0.0001

Data Index: 937240 (C4 (Web Text))

Max Activating Token Index: 645