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

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

Neuron 929 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: 0.3925. Min Range: -0.3925

Max Act: 0.3925. Min Act: -0.0002

Data Index: 410751 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3703. Min Act: -0.0002

Data Index: 706844 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3450. Min Act: -0.0002

Data Index: 758065 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3410. Min Act: -0.0002

Data Index: 628631 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3359. Min Act: -0.0002

Data Index: 531551 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3347. Min Act: -0.0002

Data Index: 47633 (C4 (Web Text))

Max Activating Token Index: 701

Text #6

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3389. Min Act: -0.0002

Data Index: 664999 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3371. Min Act: -0.0002

Data Index: 1227516 (C4 (Web Text))

Max Activating Token Index: 207

Text #8

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3315. Min Act: -0.0002

Data Index: 439638 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3311. Min Act: -0.0002

Data Index: 598420 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3178. Min Act: -0.0002

Data Index: 51774 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3012. Min Act: -0.0002

Data Index: 1343956 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3046. Min Act: -0.0002

Data Index: 821891 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2976. Min Act: -0.0002

Data Index: 1086043 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2925. Min Act: -0.0002

Data Index: 680986 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3010. Min Act: -0.0002

Data Index: 1006666 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.3001. Min Act: -0.0002

Data Index: 579950 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2916. Min Act: -0.0002

Data Index: 649230 (C4 (Web Text))

Max Activating Token Index: 402

Text #18

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2929. Min Act: -0.0002

Data Index: 1160065 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 0.3925. Min Range: -0.3925

Max Act: 0.2958. Min Act: -0.0002

Data Index: 37221 (C4 (Web Text))

Max Activating Token Index: 505