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

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

Neuron 6059 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.6214. Min Range: -3.6214

Max Act: 3.4769. Min Act: -0.0000

Data Index: 1212200 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 3.6214. Min Range: -3.6214

Max Act: 3.6201. Min Act: -0.0000

Data Index: 1173189 (C4 (Web Text))

Max Activating Token Index: 255

Text #2

Max Range: 3.6214. Min Range: -3.6214

Max Act: 3.5261. Min Act: -0.0000

Data Index: 686340 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 3.6214. Min Range: -3.6214

Max Act: 3.6214. Min Act: -0.0000

Data Index: 817940 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 3.6214. Min Range: -3.6214

Max Act: 3.4539. Min Act: -0.0000

Data Index: 1155243 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 3.6214. Min Range: -3.6214

Max Act: 3.5273. Min Act: -0.0001

Data Index: 813828 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 3.6214. Min Range: -3.6214

Max Act: 3.1913. Min Act: -0.0000

Data Index: 317143 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 3.6214. Min Range: -3.6214

Max Act: 3.4555. Min Act: -0.0000

Data Index: 1145736 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 3.6214. Min Range: -3.6214

Max Act: 3.2289. Min Act: -0.0000

Data Index: 425484 (C4 (Web Text))

Max Activating Token Index: 598

Text #9

Max Range: 3.6214. Min Range: -3.6214

Max Act: 3.0520. Min Act: -0.0000

Data Index: 967938 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 3.6214. Min Range: -3.6214

Max Act: 2.9457. Min Act: -0.0000

Data Index: 406546 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 3.6214. Min Range: -3.6214

Max Act: 2.9486. Min Act: -0.0000

Data Index: 486027 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 3.6214. Min Range: -3.6214

Max Act: 2.7834. Min Act: -0.0000

Data Index: 285890 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 3.6214. Min Range: -3.6214

Max Act: 2.6590. Min Act: -0.0001

Data Index: 1116392 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 3.6214. Min Range: -3.6214

Max Act: 2.6453. Min Act: -0.0000

Data Index: 380396 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 3.6214. Min Range: -3.6214

Max Act: 2.6195. Min Act: -0.0000

Data Index: 663222 (C4 (Web Text))

Max Activating Token Index: 236

Text #16

Max Range: 3.6214. Min Range: -3.6214

Max Act: 2.7329. Min Act: -0.0000

Data Index: 709899 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 3.6214. Min Range: -3.6214

Max Act: 2.7148. Min Act: -0.0000

Data Index: 78473 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 3.6214. Min Range: -3.6214

Max Act: 2.7137. Min Act: -0.0000

Data Index: 965897 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 3.6214. Min Range: -3.6214

Max Act: 2.5752. Min Act: -0.0000

Data Index: 1343071 (C4 (Web Text))

Max Activating Token Index: 892