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

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

Neuron 3393 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: 11.0523. Min Range: -11.0523

Max Act: 11.0523. Min Act: -0.0000

Data Index: 388222 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 11.0523. Min Range: -11.0523

Max Act: 10.4313. Min Act: -0.0000

Data Index: 47662 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 11.0523. Min Range: -11.0523

Max Act: 10.0650. Min Act: -0.0000

Data Index: 1190614 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 11.0523. Min Range: -11.0523

Max Act: 10.1079. Min Act: -0.0000

Data Index: 520475 (C4 (Web Text))

Max Activating Token Index: 61

Text #4

Max Range: 11.0523. Min Range: -11.0523

Max Act: 10.0527. Min Act: -0.0000

Data Index: 435859 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 11.0523. Min Range: -11.0523

Max Act: 9.8917. Min Act: -0.0000

Data Index: 1186681 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 11.0523. Min Range: -11.0523

Max Act: 9.8091. Min Act: -0.0000

Data Index: 123065 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 11.0523. Min Range: -11.0523

Max Act: 9.9218. Min Act: -0.0000

Data Index: 101582 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 11.0523. Min Range: -11.0523

Max Act: 9.9028. Min Act: -0.0000

Data Index: 129823 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 11.0523. Min Range: -11.0523

Max Act: 10.1301. Min Act: -0.0000

Data Index: 477291 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 11.0523. Min Range: -11.0523

Max Act: 9.3673. Min Act: -0.0000

Data Index: 879004 (C4 (Web Text))

Max Activating Token Index: 71

Text #11

Max Range: 11.0523. Min Range: -11.0523

Max Act: 9.4716. Min Act: -0.0000

Data Index: 406756 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 11.0523. Min Range: -11.0523

Max Act: 9.4484. Min Act: -0.0000

Data Index: 816124 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 11.0523. Min Range: -11.0523

Max Act: 9.4666. Min Act: -0.0000

Data Index: 1212380 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 11.0523. Min Range: -11.0523

Max Act: 9.4124. Min Act: -0.0000

Data Index: 1234434 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 11.0523. Min Range: -11.0523

Max Act: 9.5571. Min Act: -0.0000

Data Index: 164855 (C4 (Web Text))

Max Activating Token Index: 143

Text #16

Max Range: 11.0523. Min Range: -11.0523

Max Act: 9.4087. Min Act: -0.0000

Data Index: 1019490 (C4 (Web Text))

Max Activating Token Index: 50

Text #17

Max Range: 11.0523. Min Range: -11.0523

Max Act: 9.8158. Min Act: -0.0000

Data Index: 1096756 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 11.0523. Min Range: -11.0523

Max Act: 9.3789. Min Act: -0.0000

Data Index: 383265 (C4 (Web Text))

Max Activating Token Index: 563

Text #19

Max Range: 11.0523. Min Range: -11.0523

Max Act: 9.4963. Min Act: -0.0000

Data Index: 633018 (C4 (Web Text))

Max Activating Token Index: 1022