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

Dataset: The Pile

Neuron 2454 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: 1.3149. Min Range: -1.3149

Max Act: 1.3149. Min Act: -0.0000

Data Index: 1615697 (The Pile)

Max Activating Token Index: 337

Text #1

Max Range: 1.3149. Min Range: -1.3149

Max Act: 1.2589. Min Act: -0.0000

Data Index: 340812 (The Pile)

Max Activating Token Index: 338

Text #2

Max Range: 1.3149. Min Range: -1.3149

Max Act: 1.1789. Min Act: -0.0000

Data Index: 1293181 (The Pile)

Max Activating Token Index: 818

Text #3

Max Range: 1.3149. Min Range: -1.3149

Max Act: 1.1764. Min Act: -0.0000

Data Index: 249979 (The Pile)

Max Activating Token Index: 329

Text #4

Max Range: 1.3149. Min Range: -1.3149

Max Act: 1.2288. Min Act: -0.0000

Data Index: 1626071 (The Pile)

Max Activating Token Index: 639

Text #5

Max Range: 1.3149. Min Range: -1.3149

Max Act: 1.1171. Min Act: -0.0000

Data Index: 18597 (The Pile)

Max Activating Token Index: 292

Text #6

Max Range: 1.3149. Min Range: -1.3149

Max Act: 1.0930. Min Act: -0.0000

Data Index: 1003754 (The Pile)

Max Activating Token Index: 167

Text #7

Max Range: 1.3149. Min Range: -1.3149

Max Act: 1.1409. Min Act: -0.0000

Data Index: 768335 (The Pile)

Max Activating Token Index: 162

Text #8

Max Range: 1.3149. Min Range: -1.3149

Max Act: 1.1896. Min Act: -0.0000

Data Index: 1944842 (The Pile)

Max Activating Token Index: 398

Text #9

Max Range: 1.3149. Min Range: -1.3149

Max Act: 1.0552. Min Act: -0.0000

Data Index: 1173013 (The Pile)

Max Activating Token Index: 225

Text #10

Max Range: 1.3149. Min Range: -1.3149

Max Act: 1.0751. Min Act: -0.0000

Data Index: 1184876 (The Pile)

Max Activating Token Index: 247

Text #11

Max Range: 1.3149. Min Range: -1.3149

Max Act: 1.0635. Min Act: -0.0000

Data Index: 1529250 (The Pile)

Max Activating Token Index: 748

Text #12

Max Range: 1.3149. Min Range: -1.3149

Max Act: 1.0786. Min Act: -0.0000

Data Index: 505980 (The Pile)

Max Activating Token Index: 650

Text #13

Max Range: 1.3149. Min Range: -1.3149

Max Act: 1.0268. Min Act: -0.0000

Data Index: 629068 (The Pile)

Max Activating Token Index: 493

Text #14

Max Range: 1.3149. Min Range: -1.3149

Max Act: 0.9916. Min Act: -0.0000

Data Index: 765077 (The Pile)

Max Activating Token Index: 212

Text #15

Max Range: 1.3149. Min Range: -1.3149

Max Act: 1.1519. Min Act: -0.0000

Data Index: 1537866 (The Pile)

Max Activating Token Index: 905

Text #16

Max Range: 1.3149. Min Range: -1.3149

Max Act: 1.0354. Min Act: -0.0000

Data Index: 96851 (The Pile)

Max Activating Token Index: 126

Text #17

Max Range: 1.3149. Min Range: -1.3149

Max Act: 1.0044. Min Act: -0.0000

Data Index: 1470044 (The Pile)

Max Activating Token Index: 302

Text #18

Max Range: 1.3149. Min Range: -1.3149

Max Act: 1.0253. Min Act: -0.0000

Data Index: 1543274 (The Pile)

Max Activating Token Index: 994

Text #19

Max Range: 1.3149. Min Range: -1.3149

Max Act: 0.9586. Min Act: -0.0000

Data Index: 3175 (The Pile)

Max Activating Token Index: 451