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

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

Neuron 3749 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.4475. Min Act: -0.0000

Data Index: 604101 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.3459. Min Act: -0.0000

Data Index: 102726 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.3019. Min Act: -0.0000

Data Index: 212038 (C4 (Web Text))

Max Activating Token Index: 433

Text #3

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.2942. Min Act: -0.0000

Data Index: 1108334 (C4 (Web Text))

Max Activating Token Index: 914

Text #4

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.2920. Min Act: -0.0000

Data Index: 485581 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.2655. Min Act: -0.0000

Data Index: 861939 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.3227. Min Act: -0.0000

Data Index: 58319 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.2073. Min Act: -0.0000

Data Index: 1148909 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.0869. Min Act: -0.0000

Data Index: 859873 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.1387. Min Act: -0.0000

Data Index: 788439 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.1254. Min Act: -0.0000

Data Index: 1235469 (C4 (Web Text))

Max Activating Token Index: 242

Text #11

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.0846. Min Act: -0.0000

Data Index: 1128858 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.0506. Min Act: -0.0000

Data Index: 654656 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.0555. Min Act: -0.0000

Data Index: 1086564 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.0873. Min Act: -0.0000

Data Index: 563682 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.0082. Min Act: -0.0000

Data Index: 974684 (C4 (Web Text))

Max Activating Token Index: 261

Text #16

Max Range: 1.4475. Min Range: -1.4475

Max Act: 0.9915. Min Act: -0.0000

Data Index: 76230 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 1.4475. Min Range: -1.4475

Max Act: 0.9953. Min Act: -0.0000

Data Index: 1349731 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 1.4475. Min Range: -1.4475

Max Act: 0.9930. Min Act: -0.0000

Data Index: 807496 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 1.4475. Min Range: -1.4475

Max Act: 1.0307. Min Act: -0.0000

Data Index: 385328 (C4 (Web Text))

Max Activating Token Index: 488