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

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

Neuron 2664 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2163. Min Range: -4.2163

Max Act: 4.2163. Min Act: -0.0001

Data Index: 963587 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 4.2163. Min Range: -4.2163

Max Act: 4.1889. Min Act: -0.0000

Data Index: 1048856 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 4.2163. Min Range: -4.2163

Max Act: 3.4297. Min Act: -0.0001

Data Index: 25433 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 4.2163. Min Range: -4.2163

Max Act: 3.1705. Min Act: -0.0001

Data Index: 315465 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 4.2163. Min Range: -4.2163

Max Act: 3.3947. Min Act: -0.0001

Data Index: 429053 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 4.2163. Min Range: -4.2163

Max Act: 3.0942. Min Act: -0.0000

Data Index: 285680 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 4.2163. Min Range: -4.2163

Max Act: 3.1914. Min Act: -0.0001

Data Index: 854121 (C4 (Web Text))

Max Activating Token Index: 147

Text #7

Max Range: 4.2163. Min Range: -4.2163

Max Act: 3.1023. Min Act: -0.0001

Data Index: 228531 (C4 (Web Text))

Max Activating Token Index: 443

Text #8

Max Range: 4.2163. Min Range: -4.2163

Max Act: 2.9356. Min Act: -0.0000

Data Index: 1108191 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 4.2163. Min Range: -4.2163

Max Act: 2.9052. Min Act: -0.0001

Data Index: 1583833 (Python Code)

Max Activating Token Index: 28

Text #10

Max Range: 4.2163. Min Range: -4.2163

Max Act: 2.9238. Min Act: -0.0000

Data Index: 1317556 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 4.2163. Min Range: -4.2163

Max Act: 3.0069. Min Act: -0.0001

Data Index: 1316784 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 4.2163. Min Range: -4.2163

Max Act: 2.9005. Min Act: -0.0001

Data Index: 1335781 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 4.2163. Min Range: -4.2163

Max Act: 3.0300. Min Act: -0.0001

Data Index: 320514 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 4.2163. Min Range: -4.2163

Max Act: 3.1515. Min Act: -0.0001

Data Index: 419245 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 4.2163. Min Range: -4.2163

Max Act: 3.3085. Min Act: -0.0001

Data Index: 915244 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 4.2163. Min Range: -4.2163

Max Act: 3.0687. Min Act: -0.0001

Data Index: 575595 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 4.2163. Min Range: -4.2163

Max Act: 3.0620. Min Act: -0.0001

Data Index: 1163042 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 4.2163. Min Range: -4.2163

Max Act: 3.1796. Min Act: -0.0001

Data Index: 707624 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 4.2163. Min Range: -4.2163

Max Act: 2.9243. Min Act: -0.0001

Data Index: 339614 (C4 (Web Text))

Max Activating Token Index: 431