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

Dataset: The Pile

Neuron 2781 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: 1.4100. Min Range: -1.4100

Max Act: 1.4100. Min Act: -0.0000

Data Index: 1939444 (The Pile)

Max Activating Token Index: 166

Text #1

Max Range: 1.4100. Min Range: -1.4100

Max Act: 1.3157. Min Act: -0.0000

Data Index: 244568 (The Pile)

Max Activating Token Index: 167

Text #2

Max Range: 1.4100. Min Range: -1.4100

Max Act: 1.3425. Min Act: -0.0000

Data Index: 1832758 (The Pile)

Max Activating Token Index: 259

Text #3

Max Range: 1.4100. Min Range: -1.4100

Max Act: 1.0231. Min Act: -0.0000

Data Index: 393582 (The Pile)

Max Activating Token Index: 173

Text #4

Max Range: 1.4100. Min Range: -1.4100

Max Act: 1.3560. Min Act: -0.0000

Data Index: 437731 (The Pile)

Max Activating Token Index: 259

Text #5

Max Range: 1.4100. Min Range: -1.4100

Max Act: 1.2823. Min Act: -0.0000

Data Index: 1713701 (The Pile)

Max Activating Token Index: 175

Text #6

Max Range: 1.4100. Min Range: -1.4100

Max Act: 1.2877. Min Act: -0.0000

Data Index: 1311139 (The Pile)

Max Activating Token Index: 596

Text #7

Max Range: 1.4100. Min Range: -1.4100

Max Act: 1.1642. Min Act: -0.0000

Data Index: 1459257 (The Pile)

Max Activating Token Index: 388

Text #8

Max Range: 1.4100. Min Range: -1.4100

Max Act: 1.0783. Min Act: -0.0000

Data Index: 632993 (The Pile)

Max Activating Token Index: 538

Text #9

Max Range: 1.4100. Min Range: -1.4100

Max Act: 1.1794. Min Act: -0.0000

Data Index: 7515 (The Pile)

Max Activating Token Index: 908

Text #10

Max Range: 1.4100. Min Range: -1.4100

Max Act: 1.0922. Min Act: -0.0000

Data Index: 102548 (The Pile)

Max Activating Token Index: 41

Text #11

Max Range: 1.4100. Min Range: -1.4100

Max Act: 1.0099. Min Act: 0.0000

Data Index: 1718420 (The Pile)

Max Activating Token Index: 243

Text #12

Max Range: 1.4100. Min Range: -1.4100

Max Act: 0.9968. Min Act: -0.0000

Data Index: 1094179 (The Pile)

Max Activating Token Index: 990

Text #13

Max Range: 1.4100. Min Range: -1.4100

Max Act: 1.0344. Min Act: -0.0000

Data Index: 1393398 (The Pile)

Max Activating Token Index: 207

Text #14

Max Range: 1.4100. Min Range: -1.4100

Max Act: 0.9160. Min Act: -0.0000

Data Index: 1465086 (The Pile)

Max Activating Token Index: 934

Text #15

Max Range: 1.4100. Min Range: -1.4100

Max Act: 0.9010. Min Act: -0.0000

Data Index: 1472511 (The Pile)

Max Activating Token Index: 939

Text #16

Max Range: 1.4100. Min Range: -1.4100

Max Act: 0.9270. Min Act: -0.0000

Data Index: 1453610 (The Pile)

Max Activating Token Index: 557

Text #17

Max Range: 1.4100. Min Range: -1.4100

Max Act: 0.9427. Min Act: -0.0000

Data Index: 1948928 (The Pile)

Max Activating Token Index: 309

Text #18

Max Range: 1.4100. Min Range: -1.4100

Max Act: 1.0523. Min Act: -0.0000

Data Index: 1270028 (The Pile)

Max Activating Token Index: 460

Text #19

Max Range: 1.4100. Min Range: -1.4100

Max Act: 0.9561. Min Act: -0.0000

Data Index: 1485989 (The Pile)

Max Activating Token Index: 612