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

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

Neuron 3064 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.9091. Min Act: -0.0000

Data Index: 1003272 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.7544. Min Act: -0.0000

Data Index: 305610 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.7837. Min Act: -0.0000

Data Index: 848942 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.6622. Min Act: -0.0000

Data Index: 489775 (C4 (Web Text))

Max Activating Token Index: 87

Text #4

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.6719. Min Act: -0.0000

Data Index: 749324 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.6108. Min Act: -0.0000

Data Index: 911143 (C4 (Web Text))

Max Activating Token Index: 404

Text #6

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.6149. Min Act: -0.0000

Data Index: 929077 (C4 (Web Text))

Max Activating Token Index: 898

Text #7

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.5979. Min Act: -0.0000

Data Index: 780757 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.6038. Min Act: -0.0000

Data Index: 572701 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.5866. Min Act: -0.0000

Data Index: 1347583 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.6225. Min Act: -0.0000

Data Index: 235724 (C4 (Web Text))

Max Activating Token Index: 129

Text #11

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.6209. Min Act: -0.0000

Data Index: 1106406 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.5952. Min Act: -0.0000

Data Index: 926971 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.5782. Min Act: -0.0000

Data Index: 888936 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.5720. Min Act: -0.0000

Data Index: 614779 (C4 (Web Text))

Max Activating Token Index: 633

Text #15

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.5429. Min Act: -0.0000

Data Index: 1047177 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.5591. Min Act: -0.0000

Data Index: 132312 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.5543. Min Act: -0.0000

Data Index: 145421 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.5295. Min Act: -0.0000

Data Index: 85228 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 0.9091. Min Range: -0.9091

Max Act: 0.5299. Min Act: -0.0000

Data Index: 1230801 (C4 (Web Text))

Max Activating Token Index: 201