Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2241 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.3347. Min Act: -0.0000

Data Index: 148945 (The Pile)

Max Activating Token Index: 34

Text #1

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.3350. Min Act: -0.0000

Data Index: 661371 (The Pile)

Max Activating Token Index: 1010

Text #2

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2993. Min Act: -0.0000

Data Index: 1921104 (The Pile)

Max Activating Token Index: 876

Text #3

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.3174. Min Act: -0.0000

Data Index: 458846 (The Pile)

Max Activating Token Index: 67

Text #4

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.3130. Min Act: -0.0000

Data Index: 429341 (The Pile)

Max Activating Token Index: 943

Text #5

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.3135. Min Act: -0.0000

Data Index: 1647128 (The Pile)

Max Activating Token Index: 211

Text #6

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.3053. Min Act: -0.0000

Data Index: 1436413 (The Pile)

Max Activating Token Index: 827

Text #7

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2916. Min Act: -0.0000

Data Index: 90225 (The Pile)

Max Activating Token Index: 589

Text #8

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2986. Min Act: 0.0000

Data Index: 771384 (The Pile)

Max Activating Token Index: 73

Text #9

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.3077. Min Act: -0.0000

Data Index: 1692419 (The Pile)

Max Activating Token Index: 399

Text #10

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2821. Min Act: -0.0000

Data Index: 1470028 (The Pile)

Max Activating Token Index: 627

Text #11

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2951. Min Act: -0.0000

Data Index: 1845324 (The Pile)

Max Activating Token Index: 595

Text #12

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2842. Min Act: -0.0000

Data Index: 414768 (The Pile)

Max Activating Token Index: 146

Text #13

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2877. Min Act: -0.0000

Data Index: 365262 (The Pile)

Max Activating Token Index: 329

Text #14

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2843. Min Act: -0.0000

Data Index: 1479256 (The Pile)

Max Activating Token Index: 669

Text #15

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2662. Min Act: -0.0000

Data Index: 1280721 (The Pile)

Max Activating Token Index: 68

Text #16

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2908. Min Act: -0.0000

Data Index: 1049322 (The Pile)

Max Activating Token Index: 151

Text #17

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2779. Min Act: -0.0000

Data Index: 718343 (The Pile)

Max Activating Token Index: 973

Text #18

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2772. Min Act: 0.0000

Data Index: 271774 (The Pile)

Max Activating Token Index: 297

Text #19

Max Range: 0.3350. Min Range: -0.3350

Max Act: 0.2510. Min Act: -0.0000

Data Index: 514908 (The Pile)

Max Activating Token Index: 747