Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 462 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.6986. Min Act: -0.0001

Data Index: 15118 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.6799. Min Act: -0.0000

Data Index: 1006145 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.6726. Min Act: -0.0001

Data Index: 1638657 (Python Code)

Max Activating Token Index: 143

Text #3

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.6727. Min Act: -0.0001

Data Index: 1519699 (Python Code)

Max Activating Token Index: 287

Text #4

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.6375. Min Act: -0.0001

Data Index: 1394032 (Python Code)

Max Activating Token Index: 785

Text #5

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.6199. Min Act: -0.0001

Data Index: 1649711 (Python Code)

Max Activating Token Index: 325

Text #6

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5903. Min Act: -0.0001

Data Index: 1167111 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.6156. Min Act: -0.0001

Data Index: 1136145 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5857. Min Act: -0.0000

Data Index: 292361 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.6952. Min Act: -0.0001

Data Index: 1390766 (Python Code)

Max Activating Token Index: 89

Text #10

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5981. Min Act: -0.0000

Data Index: 667278 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5784. Min Act: -0.0001

Data Index: 1565265 (Python Code)

Max Activating Token Index: 913

Text #12

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5729. Min Act: -0.0000

Data Index: 1521869 (Python Code)

Max Activating Token Index: 858

Text #13

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.6071. Min Act: -0.0001

Data Index: 1655878 (Python Code)

Max Activating Token Index: 349

Text #14

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.6056. Min Act: -0.0000

Data Index: 223752 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5397. Min Act: -0.0001

Data Index: 1532969 (Python Code)

Max Activating Token Index: 448

Text #16

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5312. Min Act: -0.0001

Data Index: 1493867 (Python Code)

Max Activating Token Index: 559

Text #17

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5397. Min Act: -0.0001

Data Index: 1501139 (Python Code)

Max Activating Token Index: 494

Text #18

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5636. Min Act: -0.0001

Data Index: 1525052 (Python Code)

Max Activating Token Index: 825

Text #19

Max Range: 0.6986. Min Range: -0.6986

Max Act: 0.5456. Min Act: -0.0001

Data Index: 1563127 (Python Code)

Max Activating Token Index: 917