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

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

Neuron 5995 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2124. Min Range: -1.2124

Max Act: 1.2124. Min Act: -0.0001

Data Index: 606784 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 1.2124. Min Range: -1.2124

Max Act: 1.1029. Min Act: -0.0001

Data Index: 925233 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 1.2124. Min Range: -1.2124

Max Act: 0.8340. Min Act: -0.0001

Data Index: 299682 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 1.2124. Min Range: -1.2124

Max Act: 0.9011. Min Act: -0.0001

Data Index: 841585 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 1.2124. Min Range: -1.2124

Max Act: 0.8575. Min Act: -0.0001

Data Index: 373821 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 1.2124. Min Range: -1.2124

Max Act: 0.8181. Min Act: -0.0001

Data Index: 390871 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 1.2124. Min Range: -1.2124

Max Act: 0.8721. Min Act: -0.0001

Data Index: 850770 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 1.2124. Min Range: -1.2124

Max Act: 0.7527. Min Act: -0.0001

Data Index: 1161115 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 1.2124. Min Range: -1.2124

Max Act: 0.7384. Min Act: -0.0001

Data Index: 1242528 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 1.2124. Min Range: -1.2124

Max Act: 0.8166. Min Act: -0.0001

Data Index: 801976 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 1.2124. Min Range: -1.2124

Max Act: 0.7126. Min Act: -0.0001

Data Index: 1250286 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 1.2124. Min Range: -1.2124

Max Act: 0.8848. Min Act: -0.0001

Data Index: 1535389 (Python Code)

Max Activating Token Index: 12

Text #12

Max Range: 1.2124. Min Range: -1.2124

Max Act: 0.7757. Min Act: -0.0001

Data Index: 1509487 (Python Code)

Max Activating Token Index: 4

Text #13

Max Range: 1.2124. Min Range: -1.2124

Max Act: 0.7218. Min Act: -0.0001

Data Index: 1221043 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 1.2124. Min Range: -1.2124

Max Act: 0.7559. Min Act: -0.0001

Data Index: 279453 (C4 (Web Text))

Max Activating Token Index: 748

Text #15

Max Range: 1.2124. Min Range: -1.2124

Max Act: 0.7422. Min Act: -0.0001

Data Index: 1312740 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 1.2124. Min Range: -1.2124

Max Act: 0.6520. Min Act: -0.0001

Data Index: 432348 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 1.2124. Min Range: -1.2124

Max Act: 0.7577. Min Act: -0.0001

Data Index: 431063 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 1.2124. Min Range: -1.2124

Max Act: 0.6391. Min Act: -0.0001

Data Index: 1001077 (C4 (Web Text))

Max Activating Token Index: 954

Text #19

Max Range: 1.2124. Min Range: -1.2124

Max Act: 0.6456. Min Act: -0.0001

Data Index: 1639269 (Python Code)

Max Activating Token Index: 978