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

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

Neuron 5090 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.5181. Min Act: -0.0000

Data Index: 801647 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.4567. Min Act: -0.0000

Data Index: 924357 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.2005. Min Act: -0.0000

Data Index: 178787 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.0395. Min Act: -0.0000

Data Index: 1007004 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 3.5181. Min Range: -3.5181

Max Act: 3.0691. Min Act: -0.0000

Data Index: 179843 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 3.5181. Min Range: -3.5181

Max Act: 2.9665. Min Act: -0.0000

Data Index: 23630 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 3.5181. Min Range: -3.5181

Max Act: 2.8351. Min Act: -0.0000

Data Index: 138077 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 3.5181. Min Range: -3.5181

Max Act: 2.8319. Min Act: -0.0000

Data Index: 366573 (C4 (Web Text))

Max Activating Token Index: 192

Text #8

Max Range: 3.5181. Min Range: -3.5181

Max Act: 2.7853. Min Act: -0.0000

Data Index: 106054 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 3.5181. Min Range: -3.5181

Max Act: 2.6746. Min Act: -0.0000

Data Index: 912982 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 3.5181. Min Range: -3.5181

Max Act: 2.3723. Min Act: -0.0000

Data Index: 1099255 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 3.5181. Min Range: -3.5181

Max Act: 2.5605. Min Act: -0.0000

Data Index: 292238 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 3.5181. Min Range: -3.5181

Max Act: 2.5559. Min Act: -0.0000

Data Index: 1170725 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 3.5181. Min Range: -3.5181

Max Act: 2.5136. Min Act: -0.0000

Data Index: 1357320 (C4 (Web Text))

Max Activating Token Index: 644

Text #14

Max Range: 3.5181. Min Range: -3.5181

Max Act: 2.2613. Min Act: -0.0000

Data Index: 1324169 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 3.5181. Min Range: -3.5181

Max Act: 2.4806. Min Act: -0.0000

Data Index: 709147 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 3.5181. Min Range: -3.5181

Max Act: 2.6100. Min Act: -0.0000

Data Index: 999714 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 3.5181. Min Range: -3.5181

Max Act: 2.3292. Min Act: -0.0000

Data Index: 1266845 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 3.5181. Min Range: -3.5181

Max Act: 2.3152. Min Act: -0.0000

Data Index: 858300 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 3.5181. Min Range: -3.5181

Max Act: 2.4051. Min Act: -0.0000

Data Index: 628817 (C4 (Web Text))

Max Activating Token Index: 118