Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 696 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0236. Min Range: -1.0236

Max Act: 1.0236. Min Act: -0.0003

Data Index: 1249598 (C4 (Web Text))

Max Activating Token Index: 1010

Text #1

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.9585. Min Act: -0.0003

Data Index: 234362 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.9517. Min Act: -0.0003

Data Index: 501017 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.9103. Min Act: -0.0003

Data Index: 778730 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.8744. Min Act: -0.0003

Data Index: 1234544 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.8516. Min Act: -0.0003

Data Index: 745660 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.8498. Min Act: -0.0003

Data Index: 1354418 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.8724. Min Act: -0.0003

Data Index: 899621 (C4 (Web Text))

Max Activating Token Index: 924

Text #8

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.9145. Min Act: -0.0003

Data Index: 682539 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.8307. Min Act: -0.0003

Data Index: 1152523 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.8285. Min Act: -0.0003

Data Index: 1219709 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.8288. Min Act: -0.0003

Data Index: 261856 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.7998. Min Act: -0.0003

Data Index: 1260554 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.7644. Min Act: -0.0003

Data Index: 404425 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.8720. Min Act: -0.0003

Data Index: 383 (C4 (Web Text))

Max Activating Token Index: 730

Text #15

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.8384. Min Act: -0.0003

Data Index: 1345257 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.8063. Min Act: -0.0003

Data Index: 989520 (C4 (Web Text))

Max Activating Token Index: 869

Text #17

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.7926. Min Act: -0.0003

Data Index: 1136330 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.8967. Min Act: -0.0003

Data Index: 542460 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 1.0236. Min Range: -1.0236

Max Act: 0.8098. Min Act: -0.0003

Data Index: 512176 (C4 (Web Text))

Max Activating Token Index: 61