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

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

Neuron 178 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.8604. Min Act: -0.0001

Data Index: 1099938 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.8065. Min Act: -0.0001

Data Index: 560142 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.8332. Min Act: -0.0001

Data Index: 937537 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.8228. Min Act: -0.0001

Data Index: 976544 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7911. Min Act: -0.0001

Data Index: 950885 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7189. Min Act: -0.0001

Data Index: 1138344 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7336. Min Act: -0.0001

Data Index: 8215 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7339. Min Act: -0.0001

Data Index: 133014 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.6972. Min Act: -0.0001

Data Index: 577194 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7006. Min Act: -0.0001

Data Index: 898030 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7669. Min Act: -0.0001

Data Index: 213212 (C4 (Web Text))

Max Activating Token Index: 983

Text #11

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7485. Min Act: -0.0001

Data Index: 1250382 (C4 (Web Text))

Max Activating Token Index: 503

Text #12

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7024. Min Act: -0.0001

Data Index: 509669 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.6943. Min Act: -0.0001

Data Index: 824503 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7196. Min Act: -0.0001

Data Index: 236662 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.6938. Min Act: -0.0001

Data Index: 1110804 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.6858. Min Act: -0.0001

Data Index: 249423 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7365. Min Act: -0.0001

Data Index: 949991 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.6888. Min Act: -0.0001

Data Index: 1177096 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7132. Min Act: -0.0001

Data Index: 1313951 (C4 (Web Text))

Max Activating Token Index: 813