Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3460 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4913. Min Range: -1.4913

Max Act: 1.4045. Min Act: -0.0000

Data Index: 1250413 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 1.4913. Min Range: -1.4913

Max Act: 1.4780. Min Act: -0.0000

Data Index: 570095 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 1.4913. Min Range: -1.4913

Max Act: 1.4036. Min Act: -0.0000

Data Index: 1077640 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 1.4913. Min Range: -1.4913

Max Act: 1.4727. Min Act: -0.0000

Data Index: 954086 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 1.4913. Min Range: -1.4913

Max Act: 1.3003. Min Act: -0.0000

Data Index: 121327 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 1.4913. Min Range: -1.4913

Max Act: 1.3982. Min Act: -0.0000

Data Index: 638644 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 1.4913. Min Range: -1.4913

Max Act: 1.4913. Min Act: -0.0000

Data Index: 603095 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 1.4913. Min Range: -1.4913

Max Act: 1.3777. Min Act: -0.0000

Data Index: 406336 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 1.4913. Min Range: -1.4913

Max Act: 1.2841. Min Act: -0.0000

Data Index: 94193 (C4 (Web Text))

Max Activating Token Index: 433

Text #9

Max Range: 1.4913. Min Range: -1.4913

Max Act: 1.4426. Min Act: -0.0000

Data Index: 810679 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 1.4913. Min Range: -1.4913

Max Act: 1.2568. Min Act: -0.0000

Data Index: 481570 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 1.4913. Min Range: -1.4913

Max Act: 1.2275. Min Act: -0.0000

Data Index: 831130 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 1.4913. Min Range: -1.4913

Max Act: 1.2260. Min Act: -0.0000

Data Index: 535541 (C4 (Web Text))

Max Activating Token Index: 675

Text #13

Max Range: 1.4913. Min Range: -1.4913

Max Act: 1.3283. Min Act: -0.0000

Data Index: 1263145 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 1.4913. Min Range: -1.4913

Max Act: 1.3477. Min Act: -0.0001

Data Index: 366599 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 1.4913. Min Range: -1.4913

Max Act: 1.1842. Min Act: -0.0000

Data Index: 1300202 (C4 (Web Text))

Max Activating Token Index: 198

Text #16

Max Range: 1.4913. Min Range: -1.4913

Max Act: 1.2038. Min Act: -0.0001

Data Index: 585439 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 1.4913. Min Range: -1.4913

Max Act: 1.1988. Min Act: -0.0000

Data Index: 283511 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 1.4913. Min Range: -1.4913

Max Act: 1.2125. Min Act: -0.0000

Data Index: 894364 (C4 (Web Text))

Max Activating Token Index: 791

Text #19

Max Range: 1.4913. Min Range: -1.4913

Max Act: 1.1882. Min Act: -0.0000

Data Index: 564478 (C4 (Web Text))

Max Activating Token Index: 526