Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3648 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.3910. Min Act: -0.0000

Data Index: 45467 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.3433. Min Act: -0.0000

Data Index: 1232912 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.3377. Min Act: -0.0000

Data Index: 951076 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.3405. Min Act: -0.0000

Data Index: 1321053 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.3305. Min Act: -0.0000

Data Index: 1058827 (C4 (Web Text))

Max Activating Token Index: 541

Text #5

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.3093. Min Act: 0.0001

Data Index: 817373 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.3197. Min Act: -0.0000

Data Index: 750298 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.2826. Min Act: -0.0000

Data Index: 375497 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.2784. Min Act: -0.0000

Data Index: 205371 (C4 (Web Text))

Max Activating Token Index: 465

Text #9

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.2658. Min Act: -0.0000

Data Index: 984703 (C4 (Web Text))

Max Activating Token Index: 532

Text #10

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.2638. Min Act: -0.0000

Data Index: 754965 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.2545. Min Act: -0.0000

Data Index: 1101064 (C4 (Web Text))

Max Activating Token Index: 332

Text #12

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.2601. Min Act: 0.0000

Data Index: 1056351 (C4 (Web Text))

Max Activating Token Index: 18

Text #13

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.2474. Min Act: -0.0000

Data Index: 1316165 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.2385. Min Act: -0.0000

Data Index: 520587 (C4 (Web Text))

Max Activating Token Index: 332

Text #15

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.2354. Min Act: -0.0000

Data Index: 1017221 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.2590. Min Act: -0.0000

Data Index: 1280748 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.2367. Min Act: -0.0000

Data Index: 613238 (C4 (Web Text))

Max Activating Token Index: 987

Text #18

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.2461. Min Act: -0.0000

Data Index: 1266027 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 0.3910. Min Range: -0.3910

Max Act: 0.2385. Min Act: -0.0000

Data Index: 611097 (C4 (Web Text))

Max Activating Token Index: 505