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

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

Neuron 3742 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.9510. Min Act: -0.0000

Data Index: 912861 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.6292. Min Act: -0.0001

Data Index: 639672 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.6623. Min Act: -0.0000

Data Index: 69154 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.6620. Min Act: -0.0000

Data Index: 337248 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.6095. Min Act: -0.0000

Data Index: 1317984 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.5615. Min Act: -0.0001

Data Index: 881552 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.4670. Min Act: -0.0000

Data Index: 212810 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.4802. Min Act: -0.0001

Data Index: 163388 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.4647. Min Act: -0.0000

Data Index: 762610 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.4055. Min Act: -0.0000

Data Index: 209002 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.4697. Min Act: -0.0000

Data Index: 244973 (C4 (Web Text))

Max Activating Token Index: 855

Text #11

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.4740. Min Act: -0.0000

Data Index: 443904 (C4 (Web Text))

Max Activating Token Index: 234

Text #12

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.4503. Min Act: -0.0000

Data Index: 474540 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.4762. Min Act: -0.0000

Data Index: 636067 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.4308. Min Act: -0.0000

Data Index: 1058908 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.4222. Min Act: -0.0001

Data Index: 458089 (C4 (Web Text))

Max Activating Token Index: 634

Text #16

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.4514. Min Act: -0.0000

Data Index: 367758 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.4082. Min Act: -0.0000

Data Index: 1254371 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.4006. Min Act: -0.0001

Data Index: 849523 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 1.9510. Min Range: -1.9510

Max Act: 1.3975. Min Act: -0.0000

Data Index: 1306094 (C4 (Web Text))

Max Activating Token Index: 18