Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1121 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.4456. Min Act: -0.0001

Data Index: 1297787 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3565. Min Act: -0.0001

Data Index: 1645796 (Python Code)

Max Activating Token Index: 210

Text #2

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3425. Min Act: -0.0001

Data Index: 1378624 (Python Code)

Max Activating Token Index: 155

Text #3

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3511. Min Act: -0.0001

Data Index: 370005 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3387. Min Act: -0.0001

Data Index: 501494 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3319. Min Act: -0.0001

Data Index: 1590824 (Python Code)

Max Activating Token Index: 19

Text #6

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3304. Min Act: -0.0001

Data Index: 1598433 (Python Code)

Max Activating Token Index: 394

Text #7

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3138. Min Act: -0.0001

Data Index: 1492727 (Python Code)

Max Activating Token Index: 41

Text #8

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3125. Min Act: -0.0001

Data Index: 1487252 (Python Code)

Max Activating Token Index: 162

Text #9

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3233. Min Act: -0.0001

Data Index: 1430436 (Python Code)

Max Activating Token Index: 114

Text #10

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3189. Min Act: -0.0001

Data Index: 703448 (C4 (Web Text))

Max Activating Token Index: 667

Text #11

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3397. Min Act: -0.0001

Data Index: 1147328 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3132. Min Act: -0.0001

Data Index: 124250 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3013. Min Act: -0.0001

Data Index: 1598808 (Python Code)

Max Activating Token Index: 151

Text #14

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3100. Min Act: -0.0001

Data Index: 1644233 (Python Code)

Max Activating Token Index: 353

Text #15

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2938. Min Act: -0.0001

Data Index: 1430428 (Python Code)

Max Activating Token Index: 866

Text #16

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3146. Min Act: -0.0001

Data Index: 72356 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3029. Min Act: -0.0001

Data Index: 73092 (C4 (Web Text))

Max Activating Token Index: 775

Text #18

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.2601. Min Act: -0.0001

Data Index: 567797 (C4 (Web Text))

Max Activating Token Index: 910

Text #19

Max Range: 0.4456. Min Range: -0.4456

Max Act: 0.3059. Min Act: -0.0001

Data Index: 989207 (C4 (Web Text))

Max Activating Token Index: 477