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

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

Neuron 502 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.9535. Min Act: -0.0000

Data Index: 679864 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.9514. Min Act: -0.0000

Data Index: 399862 (C4 (Web Text))

Max Activating Token Index: 284

Text #2

Max Range: 1.0201. Min Range: -1.0201

Max Act: 1.0148. Min Act: -0.0000

Data Index: 207702 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.9576. Min Act: -0.0000

Data Index: 3547 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.9928. Min Act: -0.0000

Data Index: 846233 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 1.0201. Min Range: -1.0201

Max Act: 1.0201. Min Act: -0.0000

Data Index: 70711 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 1.0201. Min Range: -1.0201

Max Act: 1.0082. Min Act: -0.0000

Data Index: 418419 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.9801. Min Act: -0.0000

Data Index: 305786 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.9119. Min Act: -0.0000

Data Index: 1337015 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.9070. Min Act: -0.0000

Data Index: 1006651 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.8961. Min Act: -0.0000

Data Index: 552436 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.9444. Min Act: -0.0000

Data Index: 978098 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.8243. Min Act: -0.0000

Data Index: 835650 (C4 (Web Text))

Max Activating Token Index: 362

Text #13

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.8748. Min Act: -0.0000

Data Index: 906363 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.8623. Min Act: -0.0000

Data Index: 688411 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.8109. Min Act: -0.0000

Data Index: 834665 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.9190. Min Act: -0.0000

Data Index: 186762 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.7990. Min Act: -0.0000

Data Index: 760094 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.8532. Min Act: -0.0000

Data Index: 360928 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 1.0201. Min Range: -1.0201

Max Act: 0.8185. Min Act: -0.0000

Data Index: 1583430 (Python Code)

Max Activating Token Index: 9