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

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

Neuron 3598 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3952. Min Range: -1.3952

Max Act: 1.3731. Min Act: -0.0001

Data Index: 1115115 (C4 (Web Text))

Max Activating Token Index: 269

Text #1

Max Range: 1.3952. Min Range: -1.3952

Max Act: 1.2051. Min Act: -0.0001

Data Index: 675956 (C4 (Web Text))

Max Activating Token Index: 798

Text #2

Max Range: 1.3952. Min Range: -1.3952

Max Act: 1.3952. Min Act: -0.0001

Data Index: 967086 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 1.3952. Min Range: -1.3952

Max Act: 1.3220. Min Act: -0.0001

Data Index: 1048985 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 1.3952. Min Range: -1.3952

Max Act: 1.2369. Min Act: -0.0001

Data Index: 222780 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 1.3952. Min Range: -1.3952

Max Act: 1.1906. Min Act: -0.0001

Data Index: 1329562 (C4 (Web Text))

Max Activating Token Index: 525

Text #6

Max Range: 1.3952. Min Range: -1.3952

Max Act: 1.2671. Min Act: -0.0001

Data Index: 710309 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 1.3952. Min Range: -1.3952

Max Act: 0.9439. Min Act: -0.0001

Data Index: 887281 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 1.3952. Min Range: -1.3952

Max Act: 1.1009. Min Act: -0.0001

Data Index: 688702 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 1.3952. Min Range: -1.3952

Max Act: 1.1758. Min Act: -0.0001

Data Index: 924600 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 1.3952. Min Range: -1.3952

Max Act: 1.1571. Min Act: -0.0001

Data Index: 389490 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 1.3952. Min Range: -1.3952

Max Act: 1.1428. Min Act: -0.0001

Data Index: 7596 (C4 (Web Text))

Max Activating Token Index: 641

Text #12

Max Range: 1.3952. Min Range: -1.3952

Max Act: 1.0594. Min Act: -0.0001

Data Index: 868918 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 1.3952. Min Range: -1.3952

Max Act: 1.2202. Min Act: -0.0001

Data Index: 1048297 (C4 (Web Text))

Max Activating Token Index: 448

Text #14

Max Range: 1.3952. Min Range: -1.3952

Max Act: 1.2124. Min Act: -0.0001

Data Index: 985971 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 1.3952. Min Range: -1.3952

Max Act: 1.1760. Min Act: -0.0001

Data Index: 381595 (C4 (Web Text))

Max Activating Token Index: 717

Text #16

Max Range: 1.3952. Min Range: -1.3952

Max Act: 1.1053. Min Act: -0.0001

Data Index: 589136 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 1.3952. Min Range: -1.3952

Max Act: 1.1361. Min Act: -0.0001

Data Index: 205064 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 1.3952. Min Range: -1.3952

Max Act: 1.1605. Min Act: -0.0001

Data Index: 789705 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 1.3952. Min Range: -1.3952

Max Act: 1.0820. Min Act: -0.0001

Data Index: 1072929 (C4 (Web Text))

Max Activating Token Index: 422