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

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

Neuron 1125 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1160. Min Act: -0.0001

Data Index: 159781 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1098. Min Act: -0.0001

Data Index: 36320 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1139. Min Act: -0.0001

Data Index: 213297 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0976. Min Act: -0.0001

Data Index: 493932 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1025. Min Act: -0.0001

Data Index: 8432 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0977. Min Act: -0.0001

Data Index: 1178984 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0949. Min Act: -0.0001

Data Index: 171963 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1045. Min Act: -0.0001

Data Index: 501645 (C4 (Web Text))

Max Activating Token Index: 633

Text #8

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0826. Min Act: -0.0001

Data Index: 608694 (C4 (Web Text))

Max Activating Token Index: 758

Text #9

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0885. Min Act: -0.0001

Data Index: 638461 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0945. Min Act: -0.0001

Data Index: 135595 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0858. Min Act: -0.0001

Data Index: 1436980 (Python Code)

Max Activating Token Index: 694

Text #12

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0942. Min Act: -0.0001

Data Index: 723020 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0962. Min Act: -0.0001

Data Index: 1494236 (Python Code)

Max Activating Token Index: 670

Text #14

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0906. Min Act: -0.0001

Data Index: 663236 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0841. Min Act: -0.0001

Data Index: 449064 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0855. Min Act: -0.0001

Data Index: 139421 (C4 (Web Text))

Max Activating Token Index: 163

Text #17

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0867. Min Act: -0.0001

Data Index: 1111716 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0846. Min Act: -0.0001

Data Index: 428837 (C4 (Web Text))

Max Activating Token Index: 249

Text #19

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.0873. Min Act: -0.0001

Data Index: 1173661 (C4 (Web Text))

Max Activating Token Index: 351