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

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

Neuron 4524 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: 6.0931. Min Range: -6.0931

Max Act: 5.7849. Min Act: -0.0000

Data Index: 977368 (C4 (Web Text))

Max Activating Token Index: 340

Text #1

Max Range: 6.0931. Min Range: -6.0931

Max Act: 6.0931. Min Act: -0.0000

Data Index: 945464 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 6.0931. Min Range: -6.0931

Max Act: 5.6517. Min Act: -0.0000

Data Index: 830122 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 6.0931. Min Range: -6.0931

Max Act: 5.6526. Min Act: -0.0000

Data Index: 586963 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 6.0931. Min Range: -6.0931

Max Act: 5.8258. Min Act: -0.0000

Data Index: 248787 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 6.0931. Min Range: -6.0931

Max Act: 5.4438. Min Act: -0.0000

Data Index: 899293 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 6.0931. Min Range: -6.0931

Max Act: 5.5614. Min Act: -0.0000

Data Index: 184941 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 6.0931. Min Range: -6.0931

Max Act: 5.7464. Min Act: -0.0000

Data Index: 279302 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 6.0931. Min Range: -6.0931

Max Act: 5.5074. Min Act: -0.0000

Data Index: 239617 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 6.0931. Min Range: -6.0931

Max Act: 5.3134. Min Act: -0.0000

Data Index: 626420 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 6.0931. Min Range: -6.0931

Max Act: 5.2706. Min Act: -0.0000

Data Index: 704798 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 6.0931. Min Range: -6.0931

Max Act: 5.4000. Min Act: -0.0000

Data Index: 611339 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 6.0931. Min Range: -6.0931

Max Act: 5.3911. Min Act: -0.0000

Data Index: 734958 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 6.0931. Min Range: -6.0931

Max Act: 5.5577. Min Act: -0.0000

Data Index: 149132 (C4 (Web Text))

Max Activating Token Index: 9

Text #14

Max Range: 6.0931. Min Range: -6.0931

Max Act: 5.4473. Min Act: -0.0000

Data Index: 228245 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 6.0931. Min Range: -6.0931

Max Act: 5.0921. Min Act: -0.0000

Data Index: 439966 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 6.0931. Min Range: -6.0931

Max Act: 5.2484. Min Act: -0.0000

Data Index: 328804 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 6.0931. Min Range: -6.0931

Max Act: 5.2187. Min Act: -0.0000

Data Index: 58270 (C4 (Web Text))

Max Activating Token Index: 536

Text #18

Max Range: 6.0931. Min Range: -6.0931

Max Act: 5.2181. Min Act: -0.0000

Data Index: 750504 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 6.0931. Min Range: -6.0931

Max Act: 5.3630. Min Act: -0.0000

Data Index: 825563 (C4 (Web Text))

Max Activating Token Index: 931