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

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

Neuron 3131 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: 0.8567. Min Range: -0.8567

Max Act: 0.8567. Min Act: -0.0003

Data Index: 434702 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7361. Min Act: -0.0002

Data Index: 1357482 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7140. Min Act: -0.0002

Data Index: 535992 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7416. Min Act: -0.0002

Data Index: 74763 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7226. Min Act: -0.0002

Data Index: 656710 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.7050. Min Act: -0.0002

Data Index: 311755 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6910. Min Act: -0.0002

Data Index: 700642 (C4 (Web Text))

Max Activating Token Index: 14

Text #7

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6868. Min Act: -0.0002

Data Index: 293689 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6929. Min Act: -0.0002

Data Index: 463355 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6569. Min Act: -0.0002

Data Index: 396149 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6640. Min Act: -0.0002

Data Index: 1221397 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6618. Min Act: -0.0002

Data Index: 1110758 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6624. Min Act: -0.0002

Data Index: 1064422 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6307. Min Act: -0.0002

Data Index: 883301 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6317. Min Act: -0.0002

Data Index: 1236522 (C4 (Web Text))

Max Activating Token Index: 993

Text #15

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6318. Min Act: -0.0002

Data Index: 1287313 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6285. Min Act: -0.0002

Data Index: 514705 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6408. Min Act: -0.0002

Data Index: 783891 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6349. Min Act: -0.0002

Data Index: 335219 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 0.8567. Min Range: -0.8567

Max Act: 0.6134. Min Act: -0.0002

Data Index: 1210270 (C4 (Web Text))

Max Activating Token Index: 786