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

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

Neuron 2740 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: 0.8303. Min Range: -0.8303

Max Act: 0.8303. Min Act: -0.0002

Data Index: 1112589 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.8091. Min Act: -0.0002

Data Index: 1075825 (C4 (Web Text))

Max Activating Token Index: 287

Text #2

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7956. Min Act: -0.0002

Data Index: 321237 (C4 (Web Text))

Max Activating Token Index: 186

Text #3

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7927. Min Act: -0.0002

Data Index: 991489 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7825. Min Act: -0.0002

Data Index: 306560 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7514. Min Act: -0.0002

Data Index: 102374 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7150. Min Act: -0.0002

Data Index: 1287394 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7034. Min Act: -0.0002

Data Index: 887670 (C4 (Web Text))

Max Activating Token Index: 823

Text #8

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7095. Min Act: -0.0002

Data Index: 738774 (C4 (Web Text))

Max Activating Token Index: 975

Text #9

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7121. Min Act: -0.0003

Data Index: 286015 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.7036. Min Act: -0.0002

Data Index: 1212244 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6905. Min Act: -0.0002

Data Index: 438251 (C4 (Web Text))

Max Activating Token Index: 521

Text #12

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6757. Min Act: -0.0002

Data Index: 569436 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6869. Min Act: -0.0002

Data Index: 1205292 (C4 (Web Text))

Max Activating Token Index: 875

Text #14

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6716. Min Act: -0.0002

Data Index: 756732 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6592. Min Act: -0.0002

Data Index: 618226 (C4 (Web Text))

Max Activating Token Index: 662

Text #16

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6535. Min Act: -0.0002

Data Index: 393473 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6653. Min Act: -0.0002

Data Index: 994697 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6637. Min Act: -0.0002

Data Index: 487076 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 0.8303. Min Range: -0.8303

Max Act: 0.6515. Min Act: -0.0002

Data Index: 16568 (C4 (Web Text))

Max Activating Token Index: 428