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

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

Neuron 97 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.9551. Min Act: -0.0001

Data Index: 968148 (C4 (Web Text))

Max Activating Token Index: 238

Text #1

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.9095. Min Act: -0.0001

Data Index: 299737 (C4 (Web Text))

Max Activating Token Index: 981

Text #2

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.8189. Min Act: -0.0001

Data Index: 251451 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.7942. Min Act: -0.0001

Data Index: 183401 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.7701. Min Act: -0.0001

Data Index: 804676 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.8408. Min Act: -0.0001

Data Index: 739762 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.8274. Min Act: -0.0001

Data Index: 1067488 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.8173. Min Act: -0.0001

Data Index: 394135 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.8371. Min Act: -0.0001

Data Index: 413680 (C4 (Web Text))

Max Activating Token Index: 989

Text #9

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.7798. Min Act: -0.0001

Data Index: 903514 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.7795. Min Act: -0.0001

Data Index: 715129 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.7045. Min Act: -0.0001

Data Index: 196188 (C4 (Web Text))

Max Activating Token Index: 965

Text #12

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.6711. Min Act: -0.0001

Data Index: 1077657 (C4 (Web Text))

Max Activating Token Index: 717

Text #13

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.7026. Min Act: -0.0001

Data Index: 809662 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.6140. Min Act: -0.0001

Data Index: 825503 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.6994. Min Act: -0.0001

Data Index: 876878 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.6973. Min Act: -0.0001

Data Index: 104084 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.7191. Min Act: -0.0001

Data Index: 1071501 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.6050. Min Act: -0.0001

Data Index: 812849 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 0.9551. Min Range: -0.9551

Max Act: 0.6803. Min Act: -0.0001

Data Index: 1084188 (C4 (Web Text))

Max Activating Token Index: 646