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

Dataset: The Pile

Neuron 2046 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.2438. Min Act: -0.0000

Data Index: 1977614 (The Pile)

Max Activating Token Index: 170

Text #1

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.2946. Min Act: -0.0000

Data Index: 741992 (The Pile)

Max Activating Token Index: 13

Text #2

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.2157. Min Act: -0.0000

Data Index: 1589942 (The Pile)

Max Activating Token Index: 846

Text #3

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.2210. Min Act: -0.0000

Data Index: 71835 (The Pile)

Max Activating Token Index: 596

Text #4

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.2175. Min Act: -0.0000

Data Index: 505959 (The Pile)

Max Activating Token Index: 660

Text #5

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.2431. Min Act: -0.0000

Data Index: 404679 (The Pile)

Max Activating Token Index: 758

Text #6

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.2189. Min Act: -0.0000

Data Index: 97756 (The Pile)

Max Activating Token Index: 802

Text #7

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.2028. Min Act: -0.0000

Data Index: 735151 (The Pile)

Max Activating Token Index: 700

Text #8

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.2248. Min Act: -0.0000

Data Index: 1428107 (The Pile)

Max Activating Token Index: 256

Text #9

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1923. Min Act: -0.0000

Data Index: 1660415 (The Pile)

Max Activating Token Index: 510

Text #10

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.2046. Min Act: -0.0000

Data Index: 955690 (The Pile)

Max Activating Token Index: 551

Text #11

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.2014. Min Act: -0.0000

Data Index: 885866 (The Pile)

Max Activating Token Index: 383

Text #12

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.2008. Min Act: -0.0000

Data Index: 556471 (The Pile)

Max Activating Token Index: 69

Text #13

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1794. Min Act: -0.0000

Data Index: 726445 (The Pile)

Max Activating Token Index: 336

Text #14

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1779. Min Act: -0.0000

Data Index: 75104 (The Pile)

Max Activating Token Index: 873

Text #15

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1925. Min Act: -0.0000

Data Index: 908859 (The Pile)

Max Activating Token Index: 856

Text #16

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1916. Min Act: -0.0000

Data Index: 353670 (The Pile)

Max Activating Token Index: 94

Text #17

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1977. Min Act: -0.0000

Data Index: 996808 (The Pile)

Max Activating Token Index: 265

Text #18

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1463. Min Act: -0.0000

Data Index: 410152 (The Pile)

Max Activating Token Index: 149

Text #19

Max Range: 0.2946. Min Range: -0.2946

Max Act: 0.1938. Min Act: -0.0000

Data Index: 1003113 (The Pile)

Max Activating Token Index: 1004