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

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

Neuron 2347 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.2634. Min Act: -0.0001

Data Index: 51900 (C4 (Web Text))

Max Activating Token Index: 45

Text #1

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.6963. Min Act: -0.0001

Data Index: 759449 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.5059. Min Act: -0.0001

Data Index: 1261910 (C4 (Web Text))

Max Activating Token Index: 305

Text #3

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.5037. Min Act: -0.0001

Data Index: 345946 (C4 (Web Text))

Max Activating Token Index: 557

Text #4

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.4770. Min Act: -0.0001

Data Index: 423564 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.3105. Min Act: -0.0001

Data Index: 1262696 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.4679. Min Act: -0.0001

Data Index: 196963 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.5196. Min Act: -0.0001

Data Index: 631672 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.3687. Min Act: -0.0001

Data Index: 1355170 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.4653. Min Act: -0.0001

Data Index: 239723 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.4747. Min Act: -0.0001

Data Index: 703804 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.3703. Min Act: -0.0001

Data Index: 35730 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.3983. Min Act: -0.0001

Data Index: 702529 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.3976. Min Act: -0.0001

Data Index: 12431 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.4314. Min Act: -0.0001

Data Index: 1242248 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.4191. Min Act: -0.0001

Data Index: 1286811 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.5088. Min Act: -0.0001

Data Index: 1297636 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.3333. Min Act: -0.0001

Data Index: 459045 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.3152. Min Act: -0.0001

Data Index: 25479 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 1.6963. Min Range: -1.6963

Max Act: 1.4259. Min Act: -0.0001

Data Index: 255830 (C4 (Web Text))

Max Activating Token Index: 155