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

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

Neuron 22 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: 1.6935. Min Range: -1.6935

Max Act: 1.6935. Min Act: -0.0001

Data Index: 406627 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.6505. Min Act: -0.0001

Data Index: 1240894 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.5220. Min Act: -0.0000

Data Index: 1333584 (C4 (Web Text))

Max Activating Token Index: 957

Text #3

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.5697. Min Act: -0.0000

Data Index: 844932 (C4 (Web Text))

Max Activating Token Index: 951

Text #4

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.5170. Min Act: -0.0001

Data Index: 343820 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.4845. Min Act: -0.0001

Data Index: 970933 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.5173. Min Act: -0.0001

Data Index: 487898 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.5215. Min Act: -0.0001

Data Index: 208031 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.4361. Min Act: -0.0001

Data Index: 960636 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.3569. Min Act: -0.0001

Data Index: 650795 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.3257. Min Act: -0.0001

Data Index: 1356599 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.3078. Min Act: -0.0001

Data Index: 369559 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.3675. Min Act: -0.0001

Data Index: 1185622 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.3080. Min Act: -0.0001

Data Index: 27990 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.3969. Min Act: -0.0001

Data Index: 180085 (C4 (Web Text))

Max Activating Token Index: 762

Text #15

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.3499. Min Act: -0.0001

Data Index: 168717 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.4317. Min Act: -0.0000

Data Index: 103156 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.2814. Min Act: -0.0001

Data Index: 644403 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.3399. Min Act: -0.0001

Data Index: 80763 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 1.6935. Min Range: -1.6935

Max Act: 1.3191. Min Act: -0.0001

Data Index: 1210161 (C4 (Web Text))

Max Activating Token Index: 990