Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 517 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.4032. Min Act: -0.0000

Data Index: 67903 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3618. Min Act: -0.0000

Data Index: 819617 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3603. Min Act: -0.0000

Data Index: 465744 (C4 (Web Text))

Max Activating Token Index: 312

Text #3

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3494. Min Act: -0.0000

Data Index: 357808 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3325. Min Act: -0.0000

Data Index: 178071 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3227. Min Act: -0.0000

Data Index: 260441 (C4 (Web Text))

Max Activating Token Index: 602

Text #6

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3310. Min Act: -0.0000

Data Index: 1172189 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3143. Min Act: -0.0000

Data Index: 414898 (C4 (Web Text))

Max Activating Token Index: 956

Text #8

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.2910. Min Act: -0.0000

Data Index: 370395 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3099. Min Act: -0.0000

Data Index: 871467 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.2946. Min Act: -0.0000

Data Index: 615039 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3041. Min Act: -0.0000

Data Index: 176552 (C4 (Web Text))

Max Activating Token Index: 700

Text #12

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.2856. Min Act: -0.0000

Data Index: 1114169 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.2809. Min Act: -0.0000

Data Index: 1117063 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.3105. Min Act: -0.0000

Data Index: 1076499 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.2853. Min Act: -0.0000

Data Index: 1274138 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.2908. Min Act: -0.0000

Data Index: 442536 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.2747. Min Act: -0.0000

Data Index: 1338476 (C4 (Web Text))

Max Activating Token Index: 846

Text #18

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.2686. Min Act: -0.0000

Data Index: 764880 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.4032. Min Range: -0.4032

Max Act: 0.2560. Min Act: -0.0000

Data Index: 371004 (C4 (Web Text))

Max Activating Token Index: 315