Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2174 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.0899. Min Range: -2.0899

Max Act: 2.0899. Min Act: -0.0000

Data Index: 747737 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.9130. Min Act: -0.0000

Data Index: 397165 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.9181. Min Act: -0.0000

Data Index: 1142476 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.8549. Min Act: -0.0000

Data Index: 298975 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.8134. Min Act: -0.0000

Data Index: 450818 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.7516. Min Act: -0.0000

Data Index: 1203087 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.6186. Min Act: -0.0000

Data Index: 753383 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.4140. Min Act: -0.0001

Data Index: 749215 (C4 (Web Text))

Max Activating Token Index: 81

Text #8

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.6718. Min Act: -0.0000

Data Index: 1050332 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.5343. Min Act: -0.0000

Data Index: 152081 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.5321. Min Act: -0.0000

Data Index: 893397 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.5136. Min Act: -0.0000

Data Index: 1203184 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.5071. Min Act: -0.0000

Data Index: 720920 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.5185. Min Act: -0.0000

Data Index: 89398 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.4170. Min Act: -0.0000

Data Index: 797644 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.4280. Min Act: -0.0000

Data Index: 1102981 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.3939. Min Act: -0.0000

Data Index: 1263489 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.4206. Min Act: -0.0000

Data Index: 809833 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.3452. Min Act: -0.0000

Data Index: 235541 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 2.0899. Min Range: -2.0899

Max Act: 1.2984. Min Act: -0.0000

Data Index: 895464 (C4 (Web Text))

Max Activating Token Index: 124