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

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

Neuron 4155 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3183. Min Range: -1.3183

Max Act: 1.3183. Min Act: -0.0001

Data Index: 330167 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 1.3183. Min Range: -1.3183

Max Act: 1.1135. Min Act: -0.0001

Data Index: 748714 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 1.3183. Min Range: -1.3183

Max Act: 1.0716. Min Act: -0.0001

Data Index: 1215872 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 1.3183. Min Range: -1.3183

Max Act: 1.0900. Min Act: -0.0001

Data Index: 541455 (C4 (Web Text))

Max Activating Token Index: 934

Text #4

Max Range: 1.3183. Min Range: -1.3183

Max Act: 1.0470. Min Act: -0.0001

Data Index: 582793 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 1.3183. Min Range: -1.3183

Max Act: 1.0493. Min Act: -0.0001

Data Index: 905353 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 1.3183. Min Range: -1.3183

Max Act: 1.0541. Min Act: -0.0001

Data Index: 407832 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 1.3183. Min Range: -1.3183

Max Act: 0.9355. Min Act: -0.0001

Data Index: 1369806 (Python Code)

Max Activating Token Index: 167

Text #8

Max Range: 1.3183. Min Range: -1.3183

Max Act: 0.9556. Min Act: -0.0001

Data Index: 153507 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 1.3183. Min Range: -1.3183

Max Act: 0.9502. Min Act: -0.0001

Data Index: 31820 (C4 (Web Text))

Max Activating Token Index: 264

Text #10

Max Range: 1.3183. Min Range: -1.3183

Max Act: 0.8493. Min Act: -0.0001

Data Index: 1176433 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 1.3183. Min Range: -1.3183

Max Act: 0.7971. Min Act: -0.0001

Data Index: 1164992 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 1.3183. Min Range: -1.3183

Max Act: 0.9494. Min Act: -0.0001

Data Index: 758086 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 1.3183. Min Range: -1.3183

Max Act: 0.8947. Min Act: -0.0001

Data Index: 455359 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 1.3183. Min Range: -1.3183

Max Act: 0.8957. Min Act: -0.0001

Data Index: 1046007 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 1.3183. Min Range: -1.3183

Max Act: 0.8620. Min Act: -0.0001

Data Index: 1335346 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 1.3183. Min Range: -1.3183

Max Act: 0.8120. Min Act: -0.0001

Data Index: 36913 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 1.3183. Min Range: -1.3183

Max Act: 0.8759. Min Act: -0.0001

Data Index: 474060 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 1.3183. Min Range: -1.3183

Max Act: 0.8513. Min Act: -0.0001

Data Index: 348300 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 1.3183. Min Range: -1.3183

Max Act: 0.8139. Min Act: -0.0001

Data Index: 1219189 (C4 (Web Text))

Max Activating Token Index: 695