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

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

Neuron 632 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.8730. Min Act: -0.0001

Data Index: 742129 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.8112. Min Act: -0.0001

Data Index: 184104 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.6299. Min Act: -0.0001

Data Index: 1329677 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.4511. Min Act: -0.0001

Data Index: 576963 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.3150. Min Act: -0.0001

Data Index: 793573 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.2814. Min Act: -0.0001

Data Index: 1218100 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.2758. Min Act: -0.0001

Data Index: 523199 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.2483. Min Act: -0.0001

Data Index: 979491 (C4 (Web Text))

Max Activating Token Index: 11

Text #8

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.2374. Min Act: -0.0001

Data Index: 962501 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.1489. Min Act: -0.0001

Data Index: 34023 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.1555. Min Act: -0.0001

Data Index: 317935 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.1156. Min Act: -0.0001

Data Index: 754547 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 1.8730. Min Range: -1.8730

Max Act: 0.9366. Min Act: -0.0001

Data Index: 559940 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.0148. Min Act: -0.0001

Data Index: 838472 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.2345. Min Act: -0.0001

Data Index: 832061 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 1.8730. Min Range: -1.8730

Max Act: 0.9568. Min Act: -0.0001

Data Index: 782722 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.0745. Min Act: -0.0001

Data Index: 722737 (C4 (Web Text))

Max Activating Token Index: 964

Text #17

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.0183. Min Act: -0.0001

Data Index: 1222138 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.0895. Min Act: -0.0001

Data Index: 1212476 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 1.8730. Min Range: -1.8730

Max Act: 1.0073. Min Act: -0.0001

Data Index: 1340826 (C4 (Web Text))

Max Activating Token Index: 983