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

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

Neuron 2344 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3773. Min Range: -3.3773

Max Act: 3.0228. Min Act: -0.0000

Data Index: 898910 (C4 (Web Text))

Max Activating Token Index: 375

Text #1

Max Range: 3.3773. Min Range: -3.3773

Max Act: 3.1784. Min Act: -0.0000

Data Index: 1124541 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 3.3773. Min Range: -3.3773

Max Act: 2.7707. Min Act: -0.0000

Data Index: 555657 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 3.3773. Min Range: -3.3773

Max Act: 3.3773. Min Act: -0.0000

Data Index: 260836 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 3.3773. Min Range: -3.3773

Max Act: 2.9667. Min Act: -0.0000

Data Index: 424318 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 3.3773. Min Range: -3.3773

Max Act: 2.6245. Min Act: -0.0000

Data Index: 737006 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 3.3773. Min Range: -3.3773

Max Act: 2.6835. Min Act: -0.0000

Data Index: 630467 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 3.3773. Min Range: -3.3773

Max Act: 2.4949. Min Act: -0.0000

Data Index: 563984 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 3.3773. Min Range: -3.3773

Max Act: 2.4428. Min Act: -0.0000

Data Index: 603533 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 3.3773. Min Range: -3.3773

Max Act: 2.4121. Min Act: -0.0000

Data Index: 1146299 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 3.3773. Min Range: -3.3773

Max Act: 2.3131. Min Act: -0.0000

Data Index: 109582 (C4 (Web Text))

Max Activating Token Index: 49

Text #11

Max Range: 3.3773. Min Range: -3.3773

Max Act: 2.3010. Min Act: -0.0000

Data Index: 1009199 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 3.3773. Min Range: -3.3773

Max Act: 2.2624. Min Act: -0.0000

Data Index: 432038 (C4 (Web Text))

Max Activating Token Index: 73

Text #13

Max Range: 3.3773. Min Range: -3.3773

Max Act: 2.2336. Min Act: -0.0000

Data Index: 1346309 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 3.3773. Min Range: -3.3773

Max Act: 1.9967. Min Act: -0.0000

Data Index: 888783 (C4 (Web Text))

Max Activating Token Index: 127

Text #15

Max Range: 3.3773. Min Range: -3.3773

Max Act: 2.0908. Min Act: -0.0000

Data Index: 383192 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 3.3773. Min Range: -3.3773

Max Act: 2.1995. Min Act: -0.0000

Data Index: 669733 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 3.3773. Min Range: -3.3773

Max Act: 2.1972. Min Act: -0.0000

Data Index: 314644 (C4 (Web Text))

Max Activating Token Index: 940

Text #18

Max Range: 3.3773. Min Range: -3.3773

Max Act: 2.1132. Min Act: -0.0000

Data Index: 976353 (C4 (Web Text))

Max Activating Token Index: 226

Text #19

Max Range: 3.3773. Min Range: -3.3773

Max Act: 2.0836. Min Act: -0.0000

Data Index: 996054 (C4 (Web Text))

Max Activating Token Index: 562