Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1351 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0965. Min Act: -0.0002

Data Index: 784397 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0911. Min Act: -0.0002

Data Index: 1346433 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0876. Min Act: -0.0002

Data Index: 987255 (C4 (Web Text))

Max Activating Token Index: 297

Text #3

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0860. Min Act: -0.0002

Data Index: 735268 (C4 (Web Text))

Max Activating Token Index: 172

Text #4

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0817. Min Act: -0.0002

Data Index: 1344402 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0836. Min Act: -0.0002

Data Index: 93395 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0810. Min Act: -0.0002

Data Index: 917715 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0835. Min Act: -0.0002

Data Index: 483499 (C4 (Web Text))

Max Activating Token Index: 461

Text #8

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0837. Min Act: -0.0002

Data Index: 1325677 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0809. Min Act: -0.0002

Data Index: 845038 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0793. Min Act: -0.0002

Data Index: 947646 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0800. Min Act: -0.0002

Data Index: 390465 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0758. Min Act: -0.0002

Data Index: 1040250 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0801. Min Act: -0.0002

Data Index: 573644 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0787. Min Act: -0.0002

Data Index: 750816 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0784. Min Act: -0.0002

Data Index: 135845 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0766. Min Act: -0.0002

Data Index: 56842 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0766. Min Act: -0.0002

Data Index: 421392 (C4 (Web Text))

Max Activating Token Index: 223

Text #18

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0774. Min Act: -0.0002

Data Index: 120316 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 0.0965. Min Range: -0.0965

Max Act: 0.0798. Min Act: -0.0002

Data Index: 154973 (C4 (Web Text))

Max Activating Token Index: 683