Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2866 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.8312. Min Act: -0.0001

Data Index: 960333 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.8483. Min Act: -0.0001

Data Index: 318006 (C4 (Web Text))

Max Activating Token Index: 716

Text #2

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.7510. Min Act: -0.0001

Data Index: 662189 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.7294. Min Act: -0.0000

Data Index: 61501 (C4 (Web Text))

Max Activating Token Index: 207

Text #4

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.6932. Min Act: -0.0001

Data Index: 105806 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.7472. Min Act: -0.0000

Data Index: 100524 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.6865. Min Act: -0.0001

Data Index: 754101 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.6876. Min Act: -0.0001

Data Index: 470439 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.6046. Min Act: -0.0001

Data Index: 866842 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.6040. Min Act: -0.0001

Data Index: 553142 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.5963. Min Act: -0.0000

Data Index: 655999 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.6177. Min Act: -0.0001

Data Index: 691857 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.5797. Min Act: -0.0000

Data Index: 1268662 (C4 (Web Text))

Max Activating Token Index: 429

Text #13

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.6158. Min Act: -0.0001

Data Index: 744805 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.5933. Min Act: -0.0000

Data Index: 607652 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.6065. Min Act: -0.0000

Data Index: 462074 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.5644. Min Act: -0.0000

Data Index: 25474 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.5817. Min Act: -0.0000

Data Index: 335197 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.5530. Min Act: -0.0000

Data Index: 1165008 (C4 (Web Text))

Max Activating Token Index: 601

Text #19

Max Range: 0.8483. Min Range: -0.8483

Max Act: 0.5389. Min Act: -0.0000

Data Index: 20346 (C4 (Web Text))

Max Activating Token Index: 611