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

Dataset: The Pile

Neuron 1185 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.7419. Min Act: -0.0000

Data Index: 1671185 (The Pile)

Max Activating Token Index: 632

Text #1

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.7042. Min Act: -0.0000

Data Index: 1623991 (The Pile)

Max Activating Token Index: 872

Text #2

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.5602. Min Act: -0.0000

Data Index: 1252697 (The Pile)

Max Activating Token Index: 781

Text #3

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.4820. Min Act: -0.0000

Data Index: 344756 (The Pile)

Max Activating Token Index: 730

Text #4

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.4496. Min Act: -0.0000

Data Index: 599931 (The Pile)

Max Activating Token Index: 821

Text #5

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.3393. Min Act: -0.0000

Data Index: 1657058 (The Pile)

Max Activating Token Index: 717

Text #6

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.3437. Min Act: -0.0000

Data Index: 935990 (The Pile)

Max Activating Token Index: 211

Text #7

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.3288. Min Act: -0.0000

Data Index: 853003 (The Pile)

Max Activating Token Index: 470

Text #8

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.3240. Min Act: -0.0000

Data Index: 47795 (The Pile)

Max Activating Token Index: 913

Text #9

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.3240. Min Act: -0.0000

Data Index: 1794038 (The Pile)

Max Activating Token Index: 913

Text #10

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.3272. Min Act: -0.0000

Data Index: 918492 (The Pile)

Max Activating Token Index: 332

Text #11

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.2817. Min Act: -0.0000

Data Index: 1231145 (The Pile)

Max Activating Token Index: 749

Text #12

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.2466. Min Act: -0.0000

Data Index: 141949 (The Pile)

Max Activating Token Index: 669

Text #13

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.3032. Min Act: -0.0000

Data Index: 1753093 (The Pile)

Max Activating Token Index: 15

Text #14

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.2654. Min Act: -0.0000

Data Index: 358137 (The Pile)

Max Activating Token Index: 909

Text #15

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.2328. Min Act: -0.0000

Data Index: 466616 (The Pile)

Max Activating Token Index: 497

Text #16

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.2661. Min Act: -0.0000

Data Index: 321087 (The Pile)

Max Activating Token Index: 953

Text #17

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.2076. Min Act: -0.0000

Data Index: 248834 (The Pile)

Max Activating Token Index: 189

Text #18

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.1636. Min Act: -0.0000

Data Index: 1308254 (The Pile)

Max Activating Token Index: 187

Text #19

Max Range: 1.7419. Min Range: -1.7419

Max Act: 1.2313. Min Act: -0.0000

Data Index: 931494 (The Pile)

Max Activating Token Index: 333