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

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

Neuron 4266 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7241. Min Range: -3.7241

Max Act: 3.7241. Min Act: 0.0000

Data Index: 52073 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 3.7241. Min Range: -3.7241

Max Act: 3.0103. Min Act: -0.0000

Data Index: 494919 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 3.7241. Min Range: -3.7241

Max Act: 3.0146. Min Act: -0.0000

Data Index: 145139 (C4 (Web Text))

Max Activating Token Index: 573

Text #3

Max Range: 3.7241. Min Range: -3.7241

Max Act: 2.9721. Min Act: -0.0000

Data Index: 713070 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 3.7241. Min Range: -3.7241

Max Act: 2.8543. Min Act: -0.0000

Data Index: 23494 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 3.7241. Min Range: -3.7241

Max Act: 2.7324. Min Act: -0.0000

Data Index: 105859 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 3.7241. Min Range: -3.7241

Max Act: 2.7030. Min Act: -0.0000

Data Index: 264809 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 3.7241. Min Range: -3.7241

Max Act: 2.5591. Min Act: -0.0000

Data Index: 711638 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 3.7241. Min Range: -3.7241

Max Act: 2.4224. Min Act: -0.0000

Data Index: 289771 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 3.7241. Min Range: -3.7241

Max Act: 2.5104. Min Act: -0.0000

Data Index: 771601 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 3.7241. Min Range: -3.7241

Max Act: 2.5484. Min Act: -0.0000

Data Index: 482924 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 3.7241. Min Range: -3.7241

Max Act: 2.3862. Min Act: -0.0000

Data Index: 687435 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 3.7241. Min Range: -3.7241

Max Act: 2.5036. Min Act: -0.0000

Data Index: 658481 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 3.7241. Min Range: -3.7241

Max Act: 2.4181. Min Act: -0.0000

Data Index: 141066 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 3.7241. Min Range: -3.7241

Max Act: 2.4115. Min Act: -0.0000

Data Index: 1168111 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 3.7241. Min Range: -3.7241

Max Act: 2.5337. Min Act: -0.0000

Data Index: 1292882 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 3.7241. Min Range: -3.7241

Max Act: 2.4831. Min Act: -0.0000

Data Index: 851288 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 3.7241. Min Range: -3.7241

Max Act: 2.0266. Min Act: -0.0000

Data Index: 71825 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 3.7241. Min Range: -3.7241

Max Act: 2.3082. Min Act: -0.0000

Data Index: 419752 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 3.7241. Min Range: -3.7241

Max Act: 2.3021. Min Act: -0.0000

Data Index: 1085937 (C4 (Web Text))

Max Activating Token Index: 53