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

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

Neuron 2196 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: 0.3155. Min Range: -0.3155

Max Act: 0.3155. Min Act: -0.0000

Data Index: 1122039 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.3065. Min Act: -0.0001

Data Index: 116251 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.3089. Min Act: -0.0000

Data Index: 1119092 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2805. Min Act: -0.0001

Data Index: 316536 (C4 (Web Text))

Max Activating Token Index: 318

Text #4

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2739. Min Act: -0.0001

Data Index: 1201863 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2671. Min Act: -0.0001

Data Index: 164943 (C4 (Web Text))

Max Activating Token Index: 794

Text #6

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2790. Min Act: -0.0001

Data Index: 1088482 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2704. Min Act: -0.0001

Data Index: 883817 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2533. Min Act: -0.0001

Data Index: 631508 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2694. Min Act: -0.0000

Data Index: 817105 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2598. Min Act: -0.0000

Data Index: 570707 (C4 (Web Text))

Max Activating Token Index: 404

Text #11

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2484. Min Act: -0.0000

Data Index: 613267 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2569. Min Act: -0.0001

Data Index: 640150 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2537. Min Act: -0.0000

Data Index: 843877 (C4 (Web Text))

Max Activating Token Index: 313

Text #14

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2595. Min Act: -0.0000

Data Index: 928959 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2549. Min Act: -0.0000

Data Index: 119912 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2346. Min Act: -0.0000

Data Index: 545990 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2419. Min Act: -0.0000

Data Index: 702563 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2348. Min Act: -0.0001

Data Index: 92483 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2415. Min Act: -0.0000

Data Index: 684720 (C4 (Web Text))

Max Activating Token Index: 421