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

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

Neuron 5118 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.3467. Min Act: -0.0002

Data Index: 1284464 (C4 (Web Text))

Max Activating Token Index: 225

Text #1

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.3341. Min Act: -0.0002

Data Index: 810318 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.3130. Min Act: -0.0002

Data Index: 167846 (C4 (Web Text))

Max Activating Token Index: 97

Text #3

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.2641. Min Act: -0.0002

Data Index: 843794 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.2834. Min Act: -0.0002

Data Index: 1045673 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.2651. Min Act: -0.0002

Data Index: 584939 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.2739. Min Act: -0.0002

Data Index: 1335588 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.2595. Min Act: -0.0002

Data Index: 245562 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.2507. Min Act: -0.0002

Data Index: 279957 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.2401. Min Act: -0.0002

Data Index: 693557 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.2597. Min Act: -0.0002

Data Index: 97468 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.2188. Min Act: -0.0002

Data Index: 810649 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.2391. Min Act: -0.0002

Data Index: 958332 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.2375. Min Act: -0.0002

Data Index: 192957 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.2082. Min Act: -0.0002

Data Index: 820094 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.2050. Min Act: -0.0002

Data Index: 1055886 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.2109. Min Act: -0.0002

Data Index: 151046 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.2275. Min Act: -0.0002

Data Index: 412107 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.2281. Min Act: -0.0002

Data Index: 161576 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 1.3467. Min Range: -1.3467

Max Act: 1.1893. Min Act: -0.0002

Data Index: 1285846 (C4 (Web Text))

Max Activating Token Index: 71