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

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

Neuron 3678 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.4381. Min Act: -0.0000

Data Index: 504454 (C4 (Web Text))

Max Activating Token Index: 494

Text #1

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.4296. Min Act: -0.0000

Data Index: 77383 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.4034. Min Act: -0.0000

Data Index: 241003 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3829. Min Act: -0.0000

Data Index: 1241338 (C4 (Web Text))

Max Activating Token Index: 482

Text #4

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.2947. Min Act: 0.0001

Data Index: 1288322 (C4 (Web Text))

Max Activating Token Index: 672

Text #5

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.3020. Min Act: -0.0000

Data Index: 98687 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.2858. Min Act: -0.0000

Data Index: 689370 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.2805. Min Act: -0.0000

Data Index: 1031577 (C4 (Web Text))

Max Activating Token Index: 516

Text #8

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.2817. Min Act: -0.0001

Data Index: 458675 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.2774. Min Act: -0.0000

Data Index: 892336 (C4 (Web Text))

Max Activating Token Index: 181

Text #10

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.2661. Min Act: -0.0000

Data Index: 1026065 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.2634. Min Act: -0.0000

Data Index: 376517 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.2790. Min Act: 0.0000

Data Index: 614058 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.2623. Min Act: -0.0000

Data Index: 88287 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.2602. Min Act: -0.0000

Data Index: 1066186 (C4 (Web Text))

Max Activating Token Index: 659

Text #15

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.2650. Min Act: -0.0001

Data Index: 458931 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.2700. Min Act: -0.0000

Data Index: 449736 (C4 (Web Text))

Max Activating Token Index: 658

Text #17

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.2669. Min Act: -0.0000

Data Index: 62055 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.2839. Min Act: 0.0000

Data Index: 1334097 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 0.4381. Min Range: -0.4381

Max Act: 0.2546. Min Act: -0.0000

Data Index: 1344827 (C4 (Web Text))

Max Activating Token Index: 118