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

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

Neuron 4424 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0547. Min Range: -1.0547

Max Act: 1.0547. Min Act: -0.0000

Data Index: 962533 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 1.0547. Min Range: -1.0547

Max Act: 1.0455. Min Act: -0.0000

Data Index: 425447 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.9649. Min Act: -0.0000

Data Index: 97354 (C4 (Web Text))

Max Activating Token Index: 434

Text #3

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.9443. Min Act: -0.0000

Data Index: 480342 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.9411. Min Act: -0.0000

Data Index: 1218510 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.7742. Min Act: -0.0000

Data Index: 59889 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.7553. Min Act: -0.0000

Data Index: 891402 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.7366. Min Act: -0.0000

Data Index: 1343739 (C4 (Web Text))

Max Activating Token Index: 902

Text #8

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.7094. Min Act: -0.0000

Data Index: 1122548 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.7221. Min Act: -0.0000

Data Index: 784994 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.7255. Min Act: -0.0000

Data Index: 1141603 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.6922. Min Act: -0.0000

Data Index: 985565 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.7137. Min Act: -0.0000

Data Index: 619646 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.7088. Min Act: -0.0000

Data Index: 282143 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.6614. Min Act: -0.0000

Data Index: 657266 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.6761. Min Act: -0.0000

Data Index: 485026 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.6399. Min Act: -0.0000

Data Index: 122113 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.6673. Min Act: -0.0000

Data Index: 1189759 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.6375. Min Act: -0.0000

Data Index: 328919 (C4 (Web Text))

Max Activating Token Index: 995

Text #19

Max Range: 1.0547. Min Range: -1.0547

Max Act: 0.6150. Min Act: -0.0000

Data Index: 266219 (C4 (Web Text))

Max Activating Token Index: 561