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

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

Neuron 5948 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: 3.3220. Min Range: -3.3220

Max Act: 3.3220. Min Act: -0.0000

Data Index: 289940 (C4 (Web Text))

Max Activating Token Index: 310

Text #1

Max Range: 3.3220. Min Range: -3.3220

Max Act: 3.2010. Min Act: -0.0000

Data Index: 94849 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 3.3220. Min Range: -3.3220

Max Act: 3.1609. Min Act: -0.0000

Data Index: 80025 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 3.3220. Min Range: -3.3220

Max Act: 3.0455. Min Act: -0.0000

Data Index: 1163937 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 3.3220. Min Range: -3.3220

Max Act: 3.0390. Min Act: -0.0000

Data Index: 604999 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 3.3220. Min Range: -3.3220

Max Act: 2.9828. Min Act: -0.0000

Data Index: 356838 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 3.3220. Min Range: -3.3220

Max Act: 2.8950. Min Act: -0.0000

Data Index: 134058 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 3.3220. Min Range: -3.3220

Max Act: 3.0385. Min Act: -0.0000

Data Index: 489997 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 3.3220. Min Range: -3.3220

Max Act: 2.8346. Min Act: -0.0000

Data Index: 595742 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 3.3220. Min Range: -3.3220

Max Act: 2.8124. Min Act: -0.0000

Data Index: 158067 (C4 (Web Text))

Max Activating Token Index: 75

Text #10

Max Range: 3.3220. Min Range: -3.3220

Max Act: 2.6481. Min Act: -0.0000

Data Index: 434669 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 3.3220. Min Range: -3.3220

Max Act: 2.6024. Min Act: -0.0000

Data Index: 808679 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 3.3220. Min Range: -3.3220

Max Act: 2.8372. Min Act: -0.0000

Data Index: 136102 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 3.3220. Min Range: -3.3220

Max Act: 2.6928. Min Act: -0.0000

Data Index: 384283 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 3.3220. Min Range: -3.3220

Max Act: 2.6951. Min Act: -0.0000

Data Index: 845912 (C4 (Web Text))

Max Activating Token Index: 26

Text #15

Max Range: 3.3220. Min Range: -3.3220

Max Act: 2.6940. Min Act: -0.0000

Data Index: 803322 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 3.3220. Min Range: -3.3220

Max Act: 2.6746. Min Act: -0.0000

Data Index: 145845 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 3.3220. Min Range: -3.3220

Max Act: 2.5422. Min Act: -0.0000

Data Index: 141825 (C4 (Web Text))

Max Activating Token Index: 499

Text #18

Max Range: 3.3220. Min Range: -3.3220

Max Act: 2.6668. Min Act: -0.0000

Data Index: 336442 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 3.3220. Min Range: -3.3220

Max Act: 2.6352. Min Act: -0.0000

Data Index: 379944 (C4 (Web Text))

Max Activating Token Index: 58