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

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

Neuron 1928 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.9163. Min Act: -0.0000

Data Index: 39065 (C4 (Web Text))

Max Activating Token Index: 124

Text #1

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.7772. Min Act: -0.0000

Data Index: 949857 (C4 (Web Text))

Max Activating Token Index: 538

Text #2

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.8159. Min Act: -0.0000

Data Index: 89198 (C4 (Web Text))

Max Activating Token Index: 148

Text #3

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.6961. Min Act: -0.0000

Data Index: 1051341 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.6929. Min Act: -0.0000

Data Index: 116143 (C4 (Web Text))

Max Activating Token Index: 140

Text #5

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.6973. Min Act: -0.0000

Data Index: 1106503 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.6532. Min Act: -0.0000

Data Index: 1190590 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.6406. Min Act: -0.0000

Data Index: 1234310 (C4 (Web Text))

Max Activating Token Index: 38

Text #8

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.5620. Min Act: -0.0000

Data Index: 1349964 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.5925. Min Act: -0.0000

Data Index: 1236239 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.5871. Min Act: -0.0000

Data Index: 625170 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.5870. Min Act: -0.0000

Data Index: 845261 (C4 (Web Text))

Max Activating Token Index: 633

Text #12

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.6107. Min Act: -0.0000

Data Index: 926502 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.5990. Min Act: -0.0000

Data Index: 936481 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.5969. Min Act: -0.0000

Data Index: 216590 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.6117. Min Act: -0.0000

Data Index: 1321538 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.5263. Min Act: -0.0000

Data Index: 258973 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.5594. Min Act: -0.0000

Data Index: 329100 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.5349. Min Act: -0.0000

Data Index: 584676 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.5592. Min Act: -0.0000

Data Index: 14782 (C4 (Web Text))

Max Activating Token Index: 951