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

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

Neuron 4426 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: 1.6276. Min Range: -1.6276

Max Act: 1.5634. Min Act: -0.0001

Data Index: 1015476 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.4890. Min Act: -0.0001

Data Index: 802076 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.5843. Min Act: -0.0001

Data Index: 1204178 (C4 (Web Text))

Max Activating Token Index: 937

Text #3

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.6273. Min Act: -0.0001

Data Index: 884481 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.5199. Min Act: -0.0001

Data Index: 525474 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.3619. Min Act: -0.0001

Data Index: 775122 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.5073. Min Act: -0.0001

Data Index: 587217 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.4339. Min Act: -0.0001

Data Index: 501718 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.3915. Min Act: -0.0001

Data Index: 297044 (C4 (Web Text))

Max Activating Token Index: 900

Text #9

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.4106. Min Act: -0.0001

Data Index: 339366 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.4101. Min Act: -0.0001

Data Index: 667102 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.3693. Min Act: -0.0001

Data Index: 255106 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.6233. Min Act: -0.0001

Data Index: 145874 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.5357. Min Act: -0.0001

Data Index: 1318985 (C4 (Web Text))

Max Activating Token Index: 132

Text #14

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.2669. Min Act: -0.0001

Data Index: 680472 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.4306. Min Act: -0.0001

Data Index: 201280 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.3597. Min Act: -0.0001

Data Index: 1163914 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.5285. Min Act: -0.0001

Data Index: 266114 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.6276. Min Act: -0.0001

Data Index: 1331515 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 1.6276. Min Range: -1.6276

Max Act: 1.4293. Min Act: -0.0001

Data Index: 671082 (C4 (Web Text))

Max Activating Token Index: 866