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

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

Neuron 2732 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0030. Min Range: -3.0030

Max Act: 3.0030. Min Act: -0.0000

Data Index: 746793 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.8022. Min Act: -0.0000

Data Index: 1220361 (C4 (Web Text))

Max Activating Token Index: 418

Text #2

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.9568. Min Act: -0.0000

Data Index: 233551 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.6307. Min Act: -0.0000

Data Index: 132775 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.7780. Min Act: -0.0000

Data Index: 68094 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.6001. Min Act: -0.0000

Data Index: 68887 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.5566. Min Act: -0.0000

Data Index: 174675 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.5623. Min Act: -0.0000

Data Index: 61632 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.5137. Min Act: -0.0000

Data Index: 60850 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.5841. Min Act: -0.0000

Data Index: 1127718 (C4 (Web Text))

Max Activating Token Index: 413

Text #10

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.2743. Min Act: -0.0000

Data Index: 865467 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.3088. Min Act: -0.0000

Data Index: 1107101 (C4 (Web Text))

Max Activating Token Index: 899

Text #12

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.2861. Min Act: -0.0000

Data Index: 388748 (C4 (Web Text))

Max Activating Token Index: 50

Text #13

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.5290. Min Act: -0.0000

Data Index: 213912 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.5087. Min Act: -0.0000

Data Index: 1250939 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.4703. Min Act: -0.0000

Data Index: 286221 (C4 (Web Text))

Max Activating Token Index: 89

Text #16

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.3140. Min Act: -0.0000

Data Index: 177678 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.3150. Min Act: -0.0000

Data Index: 1242849 (C4 (Web Text))

Max Activating Token Index: 1009

Text #18

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.2961. Min Act: -0.0000

Data Index: 1310901 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 3.0030. Min Range: -3.0030

Max Act: 2.2691. Min Act: -0.0000

Data Index: 882333 (C4 (Web Text))

Max Activating Token Index: 63