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

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

Neuron 2893 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8755. Min Range: -5.8755

Max Act: 5.8755. Min Act: -0.0000

Data Index: 860277 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 5.8755. Min Range: -5.8755

Max Act: 5.8465. Min Act: -0.0000

Data Index: 1242522 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 5.8755. Min Range: -5.8755

Max Act: 5.6343. Min Act: -0.0000

Data Index: 801025 (C4 (Web Text))

Max Activating Token Index: 393

Text #3

Max Range: 5.8755. Min Range: -5.8755

Max Act: 5.4482. Min Act: -0.0000

Data Index: 150796 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 5.8755. Min Range: -5.8755

Max Act: 5.4191. Min Act: -0.0000

Data Index: 311377 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 5.8755. Min Range: -5.8755

Max Act: 5.3213. Min Act: -0.0000

Data Index: 902346 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 5.8755. Min Range: -5.8755

Max Act: 5.4745. Min Act: -0.0000

Data Index: 168834 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 5.8755. Min Range: -5.8755

Max Act: 5.2276. Min Act: -0.0000

Data Index: 1056459 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 5.8755. Min Range: -5.8755

Max Act: 5.1956. Min Act: -0.0000

Data Index: 1101812 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 5.8755. Min Range: -5.8755

Max Act: 5.1788. Min Act: -0.0000

Data Index: 422368 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 5.8755. Min Range: -5.8755

Max Act: 5.1539. Min Act: -0.0000

Data Index: 920818 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 5.8755. Min Range: -5.8755

Max Act: 5.0180. Min Act: -0.0000

Data Index: 1288548 (C4 (Web Text))

Max Activating Token Index: 436

Text #12

Max Range: 5.8755. Min Range: -5.8755

Max Act: 5.0025. Min Act: -0.0000

Data Index: 1325063 (C4 (Web Text))

Max Activating Token Index: 339

Text #13

Max Range: 5.8755. Min Range: -5.8755

Max Act: 5.0465. Min Act: -0.0000

Data Index: 1154126 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 5.8755. Min Range: -5.8755

Max Act: 4.8720. Min Act: -0.0000

Data Index: 1016 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 5.8755. Min Range: -5.8755

Max Act: 4.8554. Min Act: -0.0000

Data Index: 579107 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 5.8755. Min Range: -5.8755

Max Act: 4.6379. Min Act: -0.0000

Data Index: 452885 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 5.8755. Min Range: -5.8755

Max Act: 4.6170. Min Act: -0.0000

Data Index: 646275 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 5.8755. Min Range: -5.8755

Max Act: 4.8036. Min Act: -0.0000

Data Index: 167956 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 5.8755. Min Range: -5.8755

Max Act: 4.7079. Min Act: -0.0000

Data Index: 583122 (C4 (Web Text))

Max Activating Token Index: 452