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

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

Neuron 5076 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: 1.3070. Min Range: -1.3070

Max Act: 1.3070. Min Act: -0.0002

Data Index: 238255 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.1632. Min Act: -0.0002

Data Index: 747152 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.1597. Min Act: -0.0002

Data Index: 215669 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.0772. Min Act: -0.0002

Data Index: 640284 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.0841. Min Act: -0.0002

Data Index: 671220 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.0870. Min Act: -0.0002

Data Index: 1286931 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.0644. Min Act: -0.0002

Data Index: 1083979 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.0630. Min Act: -0.0002

Data Index: 855115 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.0380. Min Act: -0.0002

Data Index: 1006607 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.0567. Min Act: -0.0003

Data Index: 640605 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.0391. Min Act: -0.0002

Data Index: 255360 (C4 (Web Text))

Max Activating Token Index: 469

Text #11

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.0353. Min Act: -0.0002

Data Index: 423850 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.0406. Min Act: -0.0002

Data Index: 68001 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.0593. Min Act: -0.0002

Data Index: 725126 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.0125. Min Act: -0.0002

Data Index: 858173 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.0266. Min Act: -0.0002

Data Index: 1059261 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.0042. Min Act: -0.0002

Data Index: 1047998 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 1.3070. Min Range: -1.3070

Max Act: 0.9981. Min Act: -0.0002

Data Index: 1500000 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.0174. Min Act: -0.0002

Data Index: 149785 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 1.3070. Min Range: -1.3070

Max Act: 1.0144. Min Act: -0.0002

Data Index: 127548 (C4 (Web Text))

Max Activating Token Index: 76