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

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

Neuron 772 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: 1.3011. Min Range: -1.3011

Max Act: 1.3011. Min Act: -0.0001

Data Index: 1358004 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 1.3011. Min Range: -1.3011

Max Act: 1.0681. Min Act: -0.0001

Data Index: 615328 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 1.3011. Min Range: -1.3011

Max Act: 1.0157. Min Act: -0.0001

Data Index: 1283261 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.9794. Min Act: -0.0001

Data Index: 290830 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.9169. Min Act: -0.0001

Data Index: 954067 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.9865. Min Act: -0.0001

Data Index: 1293739 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.9810. Min Act: -0.0001

Data Index: 770662 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.8921. Min Act: -0.0001

Data Index: 959570 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.9833. Min Act: -0.0001

Data Index: 1329297 (C4 (Web Text))

Max Activating Token Index: 583

Text #9

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.9243. Min Act: -0.0001

Data Index: 1256522 (C4 (Web Text))

Max Activating Token Index: 551

Text #10

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.8920. Min Act: -0.0001

Data Index: 759712 (C4 (Web Text))

Max Activating Token Index: 340

Text #11

Max Range: 1.3011. Min Range: -1.3011

Max Act: 1.0019. Min Act: -0.0001

Data Index: 368671 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.9510. Min Act: -0.0001

Data Index: 1339089 (C4 (Web Text))

Max Activating Token Index: 472

Text #13

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.9906. Min Act: -0.0001

Data Index: 501852 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.9115. Min Act: -0.0001

Data Index: 1161998 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.9276. Min Act: -0.0001

Data Index: 1308668 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.9300. Min Act: -0.0001

Data Index: 96810 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.9054. Min Act: -0.0001

Data Index: 1341993 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.9890. Min Act: -0.0001

Data Index: 1015588 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 1.3011. Min Range: -1.3011

Max Act: 0.9314. Min Act: -0.0001

Data Index: 45664 (C4 (Web Text))

Max Activating Token Index: 860