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

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

Neuron 3926 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: 1.8352. Min Range: -1.8352

Max Act: 1.8352. Min Act: -0.0000

Data Index: 508334 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.5822. Min Act: -0.0000

Data Index: 584467 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.5070. Min Act: -0.0000

Data Index: 29477 (C4 (Web Text))

Max Activating Token Index: 122

Text #3

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.0655. Min Act: -0.0000

Data Index: 1021367 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.0404. Min Act: -0.0000

Data Index: 82837 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.1192. Min Act: -0.0000

Data Index: 905561 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.0819. Min Act: -0.0000

Data Index: 112045 (C4 (Web Text))

Max Activating Token Index: 459

Text #7

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.0354. Min Act: -0.0000

Data Index: 740332 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.0289. Min Act: -0.0000

Data Index: 468645 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 1.8352. Min Range: -1.8352

Max Act: 0.8561. Min Act: -0.0000

Data Index: 928264 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 1.8352. Min Range: -1.8352

Max Act: 1.0032. Min Act: -0.0000

Data Index: 1343170 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 1.8352. Min Range: -1.8352

Max Act: 0.9261. Min Act: -0.0000

Data Index: 800447 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 1.8352. Min Range: -1.8352

Max Act: 0.7934. Min Act: -0.0000

Data Index: 1231162 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 1.8352. Min Range: -1.8352

Max Act: 0.8978. Min Act: -0.0000

Data Index: 421303 (C4 (Web Text))

Max Activating Token Index: 552

Text #14

Max Range: 1.8352. Min Range: -1.8352

Max Act: 0.8408. Min Act: -0.0000

Data Index: 1066354 (C4 (Web Text))

Max Activating Token Index: 468

Text #15

Max Range: 1.8352. Min Range: -1.8352

Max Act: 0.8807. Min Act: -0.0000

Data Index: 734641 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 1.8352. Min Range: -1.8352

Max Act: 0.7407. Min Act: -0.0000

Data Index: 1203485 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 1.8352. Min Range: -1.8352

Max Act: 0.7965. Min Act: -0.0000

Data Index: 1120319 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 1.8352. Min Range: -1.8352

Max Act: 0.9876. Min Act: -0.0000

Data Index: 335405 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 1.8352. Min Range: -1.8352

Max Act: 0.7885. Min Act: -0.0000

Data Index: 240644 (C4 (Web Text))

Max Activating Token Index: 617