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

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

Neuron 3637 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3904. Min Act: -0.0001

Data Index: 733265 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3294. Min Act: -0.0000

Data Index: 928578 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3295. Min Act: -0.0001

Data Index: 1241789 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3235. Min Act: -0.0001

Data Index: 178332 (C4 (Web Text))

Max Activating Token Index: 963

Text #4

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.3257. Min Act: -0.0000

Data Index: 1083360 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2911. Min Act: -0.0001

Data Index: 132354 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2912. Min Act: -0.0000

Data Index: 161081 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2941. Min Act: -0.0000

Data Index: 55598 (C4 (Web Text))

Max Activating Token Index: 767

Text #8

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2841. Min Act: -0.0001

Data Index: 926591 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.1485. Min Act: -0.0000

Data Index: 490119 (C4 (Web Text))

Max Activating Token Index: 815

Text #10

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2755. Min Act: -0.0000

Data Index: 825384 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2812. Min Act: -0.0000

Data Index: 570477 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2776. Min Act: -0.0001

Data Index: 806474 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2449. Min Act: -0.0000

Data Index: 1336955 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2745. Min Act: -0.0001

Data Index: 458149 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2692. Min Act: -0.0000

Data Index: 119430 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2737. Min Act: -0.0000

Data Index: 379351 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2609. Min Act: -0.0000

Data Index: 1325275 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2432. Min Act: -0.0001

Data Index: 1113823 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 0.3904. Min Range: -0.3904

Max Act: 0.2574. Min Act: -0.0001

Data Index: 1296389 (C4 (Web Text))

Max Activating Token Index: 644