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

Dataset: The Pile

Neuron 459 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 11.9070. Min Range: -11.9070

Max Act: 11.9070. Min Act: -0.0000

Data Index: 1085559 (The Pile)

Max Activating Token Index: 105

Text #1

Max Range: 11.9070. Min Range: -11.9070

Max Act: 11.1088. Min Act: -0.0000

Data Index: 1322891 (The Pile)

Max Activating Token Index: 27

Text #2

Max Range: 11.9070. Min Range: -11.9070

Max Act: 10.4007. Min Act: -0.0000

Data Index: 1108059 (The Pile)

Max Activating Token Index: 25

Text #3

Max Range: 11.9070. Min Range: -11.9070

Max Act: 10.7224. Min Act: -0.0000

Data Index: 80660 (The Pile)

Max Activating Token Index: 46

Text #4

Max Range: 11.9070. Min Range: -11.9070

Max Act: 10.8559. Min Act: -0.0000

Data Index: 1771090 (The Pile)

Max Activating Token Index: 210

Text #5

Max Range: 11.9070. Min Range: -11.9070

Max Act: 10.2944. Min Act: -0.0000

Data Index: 1159802 (The Pile)

Max Activating Token Index: 442

Text #6

Max Range: 11.9070. Min Range: -11.9070

Max Act: 9.2932. Min Act: -0.0000

Data Index: 1232065 (The Pile)

Max Activating Token Index: 197

Text #7

Max Range: 11.9070. Min Range: -11.9070

Max Act: 9.2088. Min Act: -0.0000

Data Index: 1969369 (The Pile)

Max Activating Token Index: 526

Text #8

Max Range: 11.9070. Min Range: -11.9070

Max Act: 9.6026. Min Act: -0.0000

Data Index: 1665683 (The Pile)

Max Activating Token Index: 538

Text #9

Max Range: 11.9070. Min Range: -11.9070

Max Act: 9.4009. Min Act: -0.0000

Data Index: 670275 (The Pile)

Max Activating Token Index: 405

Text #10

Max Range: 11.9070. Min Range: -11.9070

Max Act: 9.4458. Min Act: -0.0000

Data Index: 242894 (The Pile)

Max Activating Token Index: 353

Text #11

Max Range: 11.9070. Min Range: -11.9070

Max Act: 9.3255. Min Act: -0.0000

Data Index: 1018835 (The Pile)

Max Activating Token Index: 25

Text #12

Max Range: 11.9070. Min Range: -11.9070

Max Act: 8.9531. Min Act: -0.0000

Data Index: 1741631 (The Pile)

Max Activating Token Index: 460

Text #13

Max Range: 11.9070. Min Range: -11.9070

Max Act: 9.0662. Min Act: -0.0000

Data Index: 1715295 (The Pile)

Max Activating Token Index: 98

Text #14

Max Range: 11.9070. Min Range: -11.9070

Max Act: 8.7686. Min Act: -0.0000

Data Index: 1660590 (The Pile)

Max Activating Token Index: 227

Text #15

Max Range: 11.9070. Min Range: -11.9070

Max Act: 9.3366. Min Act: -0.0000

Data Index: 1270771 (The Pile)

Max Activating Token Index: 23

Text #16

Max Range: 11.9070. Min Range: -11.9070

Max Act: 8.8422. Min Act: -0.0000

Data Index: 1413558 (The Pile)

Max Activating Token Index: 95

Text #17

Max Range: 11.9070. Min Range: -11.9070

Max Act: 8.7375. Min Act: -0.0000

Data Index: 1757022 (The Pile)

Max Activating Token Index: 463

Text #18

Max Range: 11.9070. Min Range: -11.9070

Max Act: 7.7470. Min Act: -0.0000

Data Index: 1458639 (The Pile)

Max Activating Token Index: 36

Text #19

Max Range: 11.9070. Min Range: -11.9070

Max Act: 8.4780. Min Act: -0.0000

Data Index: 911930 (The Pile)

Max Activating Token Index: 16