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

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

Neuron 1444 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: 1.7093. Min Range: -1.7093

Max Act: 1.7030. Min Act: -0.0001

Data Index: 743878 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.5111. Min Act: -0.0001

Data Index: 1108236 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.6234. Min Act: -0.0001

Data Index: 1300184 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.7093. Min Act: -0.0001

Data Index: 672182 (C4 (Web Text))

Max Activating Token Index: 862

Text #4

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.6025. Min Act: -0.0001

Data Index: 1156442 (C4 (Web Text))

Max Activating Token Index: 585

Text #5

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.5115. Min Act: -0.0001

Data Index: 1249705 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.5870. Min Act: -0.0001

Data Index: 816656 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.4871. Min Act: -0.0001

Data Index: 652987 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.5752. Min Act: -0.0001

Data Index: 441709 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.4562. Min Act: -0.0001

Data Index: 1251591 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.5341. Min Act: -0.0001

Data Index: 84540 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.4953. Min Act: -0.0001

Data Index: 806548 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.4864. Min Act: -0.0001

Data Index: 110300 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.4545. Min Act: -0.0001

Data Index: 869140 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.4652. Min Act: -0.0001

Data Index: 947757 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.4476. Min Act: -0.0001

Data Index: 607703 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.4391. Min Act: -0.0001

Data Index: 287327 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.4122. Min Act: -0.0001

Data Index: 385134 (C4 (Web Text))

Max Activating Token Index: 630

Text #18

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.3401. Min Act: -0.0001

Data Index: 920829 (C4 (Web Text))

Max Activating Token Index: 651

Text #19

Max Range: 1.7093. Min Range: -1.7093

Max Act: 1.3433. Min Act: -0.0001

Data Index: 384156 (C4 (Web Text))

Max Activating Token Index: 795