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

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

Neuron 6054 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.5861. Min Act: -0.0000

Data Index: 1076277 (C4 (Web Text))

Max Activating Token Index: 398

Text #1

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.3428. Min Act: -0.0000

Data Index: 365890 (C4 (Web Text))

Max Activating Token Index: 731

Text #2

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.5220. Min Act: -0.0000

Data Index: 881339 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.3951. Min Act: -0.0000

Data Index: 719721 (C4 (Web Text))

Max Activating Token Index: 723

Text #4

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.3507. Min Act: -0.0000

Data Index: 595248 (C4 (Web Text))

Max Activating Token Index: 208

Text #5

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.3199. Min Act: -0.0000

Data Index: 46825 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.3985. Min Act: -0.0000

Data Index: 438623 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.3142. Min Act: -0.0000

Data Index: 263397 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.3540. Min Act: -0.0000

Data Index: 100773 (C4 (Web Text))

Max Activating Token Index: 278

Text #9

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.2764. Min Act: -0.0000

Data Index: 560250 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.2003. Min Act: -0.0000

Data Index: 472640 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.2047. Min Act: -0.0000

Data Index: 155149 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.1930. Min Act: -0.0000

Data Index: 810327 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.1869. Min Act: -0.0000

Data Index: 877547 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.2557. Min Act: -0.0000

Data Index: 74956 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.2571. Min Act: -0.0000

Data Index: 454941 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.2377. Min Act: -0.0000

Data Index: 303690 (C4 (Web Text))

Max Activating Token Index: 963

Text #17

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.1709. Min Act: -0.0000

Data Index: 702037 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.2321. Min Act: -0.0000

Data Index: 1166448 (C4 (Web Text))

Max Activating Token Index: 593

Text #19

Max Range: 1.5861. Min Range: -1.5861

Max Act: 1.2276. Min Act: -0.0000

Data Index: 413226 (C4 (Web Text))

Max Activating Token Index: 941