Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2432 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2814. Min Act: -0.0001

Data Index: 1356130 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2474. Min Act: -0.0001

Data Index: 1326037 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2308. Min Act: -0.0001

Data Index: 129034 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2230. Min Act: -0.0001

Data Index: 775834 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2203. Min Act: -0.0001

Data Index: 669139 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2161. Min Act: -0.0001

Data Index: 1216163 (C4 (Web Text))

Max Activating Token Index: 960

Text #6

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2098. Min Act: -0.0001

Data Index: 809436 (C4 (Web Text))

Max Activating Token Index: 980

Text #7

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2057. Min Act: -0.0001

Data Index: 207757 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2041. Min Act: -0.0001

Data Index: 1286325 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2048. Min Act: -0.0001

Data Index: 598153 (C4 (Web Text))

Max Activating Token Index: 852

Text #10

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2038. Min Act: -0.0001

Data Index: 191869 (C4 (Web Text))

Max Activating Token Index: 90

Text #11

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2039. Min Act: -0.0001

Data Index: 897755 (C4 (Web Text))

Max Activating Token Index: 804

Text #12

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2030. Min Act: -0.0001

Data Index: 546378 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2082. Min Act: -0.0001

Data Index: 40502 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2081. Min Act: -0.0001

Data Index: 882859 (C4 (Web Text))

Max Activating Token Index: 726

Text #15

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2077. Min Act: -0.0001

Data Index: 404844 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.1950. Min Act: -0.0001

Data Index: 546217 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2063. Min Act: -0.0001

Data Index: 850187 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.1979. Min Act: -0.0001

Data Index: 468320 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 0.2814. Min Range: -0.2814

Max Act: 0.2040. Min Act: -0.0001

Data Index: 1022201 (C4 (Web Text))

Max Activating Token Index: 273