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

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

Neuron 4591 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5577. Min Range: -0.5577

Max Act: 0.5577. Min Act: -0.0000

Data Index: 23758 (C4 (Web Text))

Max Activating Token Index: 823

Text #1

Max Range: 0.5577. Min Range: -0.5577

Max Act: 0.5293. Min Act: -0.0000

Data Index: 327207 (C4 (Web Text))

Max Activating Token Index: 854

Text #2

Max Range: 0.5577. Min Range: -0.5577

Max Act: 0.5020. Min Act: 0.0000

Data Index: 453670 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 0.5577. Min Range: -0.5577

Max Act: 0.4231. Min Act: -0.0000

Data Index: 1241040 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 0.5577. Min Range: -0.5577

Max Act: 0.4751. Min Act: -0.0000

Data Index: 234949 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 0.5577. Min Range: -0.5577

Max Act: 0.4554. Min Act: -0.0000

Data Index: 1123457 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.5577. Min Range: -0.5577

Max Act: 0.4660. Min Act: 0.0002

Data Index: 1034945 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 0.5577. Min Range: -0.5577

Max Act: 0.4598. Min Act: -0.0000

Data Index: 1318425 (C4 (Web Text))

Max Activating Token Index: 491

Text #8

Max Range: 0.5577. Min Range: -0.5577

Max Act: 0.4415. Min Act: -0.0000

Data Index: 1244819 (C4 (Web Text))

Max Activating Token Index: 998

Text #9

Max Range: 0.5577. Min Range: -0.5577

Max Act: 0.4093. Min Act: 0.0000

Data Index: 488878 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 0.5577. Min Range: -0.5577

Max Act: 0.4323. Min Act: -0.0000

Data Index: 324257 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 0.5577. Min Range: -0.5577

Max Act: 0.4361. Min Act: -0.0000

Data Index: 1085943 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 0.5577. Min Range: -0.5577

Max Act: 0.4339. Min Act: -0.0000

Data Index: 1352906 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.5577. Min Range: -0.5577

Max Act: 0.4006. Min Act: -0.0000

Data Index: 838385 (C4 (Web Text))

Max Activating Token Index: 174

Text #14

Max Range: 0.5577. Min Range: -0.5577

Max Act: 0.4152. Min Act: -0.0000

Data Index: 141718 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.5577. Min Range: -0.5577

Max Act: 0.4159. Min Act: -0.0000

Data Index: 953020 (C4 (Web Text))

Max Activating Token Index: 853

Text #16

Max Range: 0.5577. Min Range: -0.5577

Max Act: 0.4110. Min Act: -0.0000

Data Index: 539410 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 0.5577. Min Range: -0.5577

Max Act: 0.3838. Min Act: -0.0000

Data Index: 2284 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 0.5577. Min Range: -0.5577

Max Act: 0.4018. Min Act: -0.0000

Data Index: 450450 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.5577. Min Range: -0.5577

Max Act: 0.4026. Min Act: -0.0000

Data Index: 1038756 (C4 (Web Text))

Max Activating Token Index: 495