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

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

Neuron 1743 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: 2.3928. Min Range: -2.3928

Max Act: 2.3928. Min Act: -0.0002

Data Index: 1032939 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 2.3928. Min Range: -2.3928

Max Act: 2.2761. Min Act: -0.0002

Data Index: 184040 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 2.3928. Min Range: -2.3928

Max Act: 2.2573. Min Act: -0.0002

Data Index: 297892 (C4 (Web Text))

Max Activating Token Index: 58

Text #3

Max Range: 2.3928. Min Range: -2.3928

Max Act: 2.2489. Min Act: -0.0002

Data Index: 397192 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 2.3928. Min Range: -2.3928

Max Act: 2.0604. Min Act: -0.0002

Data Index: 1175578 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 2.3928. Min Range: -2.3928

Max Act: 2.0167. Min Act: -0.0002

Data Index: 1151648 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 2.3928. Min Range: -2.3928

Max Act: 2.0124. Min Act: -0.0002

Data Index: 867714 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 2.3928. Min Range: -2.3928

Max Act: 1.9989. Min Act: -0.0002

Data Index: 840241 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 2.3928. Min Range: -2.3928

Max Act: 1.9396. Min Act: -0.0002

Data Index: 738835 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 2.3928. Min Range: -2.3928

Max Act: 2.0406. Min Act: -0.0002

Data Index: 121811 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 2.3928. Min Range: -2.3928

Max Act: 2.0165. Min Act: -0.0002

Data Index: 44397 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 2.3928. Min Range: -2.3928

Max Act: 1.9723. Min Act: -0.0002

Data Index: 360232 (C4 (Web Text))

Max Activating Token Index: 421

Text #12

Max Range: 2.3928. Min Range: -2.3928

Max Act: 2.0146. Min Act: -0.0002

Data Index: 804477 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 2.3928. Min Range: -2.3928

Max Act: 1.9892. Min Act: -0.0002

Data Index: 565814 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 2.3928. Min Range: -2.3928

Max Act: 1.9685. Min Act: -0.0002

Data Index: 949741 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 2.3928. Min Range: -2.3928

Max Act: 2.0148. Min Act: -0.0002

Data Index: 550432 (C4 (Web Text))

Max Activating Token Index: 665

Text #16

Max Range: 2.3928. Min Range: -2.3928

Max Act: 1.9476. Min Act: -0.0002

Data Index: 627253 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 2.3928. Min Range: -2.3928

Max Act: 1.9913. Min Act: -0.0002

Data Index: 105961 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 2.3928. Min Range: -2.3928

Max Act: 1.9709. Min Act: -0.0002

Data Index: 1076191 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 2.3928. Min Range: -2.3928

Max Act: 1.9519. Min Act: -0.0002

Data Index: 640582 (C4 (Web Text))

Max Activating Token Index: 279