Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1810 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 9.7898. Min Range: -9.7898

Max Act: 9.7898. Min Act: -0.0000

Data Index: 1038339 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 9.7898. Min Range: -9.7898

Max Act: 9.7758. Min Act: -0.0000

Data Index: 883806 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 9.7898. Min Range: -9.7898

Max Act: 9.6666. Min Act: -0.0000

Data Index: 289121 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 9.7898. Min Range: -9.7898

Max Act: 9.5451. Min Act: -0.0000

Data Index: 34879 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 9.7898. Min Range: -9.7898

Max Act: 9.5129. Min Act: -0.0000

Data Index: 1106690 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 9.7898. Min Range: -9.7898

Max Act: 9.3701. Min Act: -0.0000

Data Index: 281567 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 9.7898. Min Range: -9.7898

Max Act: 9.2928. Min Act: -0.0000

Data Index: 1252126 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 9.7898. Min Range: -9.7898

Max Act: 8.9696. Min Act: -0.0000

Data Index: 176542 (C4 (Web Text))

Max Activating Token Index: 117

Text #8

Max Range: 9.7898. Min Range: -9.7898

Max Act: 9.0679. Min Act: -0.0000

Data Index: 1066417 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 9.7898. Min Range: -9.7898

Max Act: 9.0963. Min Act: -0.0000

Data Index: 134740 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 9.7898. Min Range: -9.7898

Max Act: 9.0620. Min Act: -0.0000

Data Index: 953310 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 9.7898. Min Range: -9.7898

Max Act: 8.7413. Min Act: -0.0000

Data Index: 294662 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 9.7898. Min Range: -9.7898

Max Act: 8.7011. Min Act: -0.0000

Data Index: 1279056 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 9.7898. Min Range: -9.7898

Max Act: 8.6735. Min Act: -0.0000

Data Index: 268394 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 9.7898. Min Range: -9.7898

Max Act: 8.8457. Min Act: -0.0000

Data Index: 1330817 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 9.7898. Min Range: -9.7898

Max Act: 8.8955. Min Act: -0.0000

Data Index: 517162 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 9.7898. Min Range: -9.7898

Max Act: 8.3995. Min Act: -0.0000

Data Index: 370108 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 9.7898. Min Range: -9.7898

Max Act: 8.7124. Min Act: -0.0000

Data Index: 1235481 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 9.7898. Min Range: -9.7898

Max Act: 8.4198. Min Act: -0.0000

Data Index: 909108 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 9.7898. Min Range: -9.7898

Max Act: 8.7331. Min Act: 0.0001

Data Index: 1030959 (C4 (Web Text))

Max Activating Token Index: 281