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

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

Neuron 1956 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8138. Min Range: -1.8138

Max Act: 1.8138. Min Act: -0.0000

Data Index: 324738 (C4 (Web Text))

Max Activating Token Index: 152

Text #1

Max Range: 1.8138. Min Range: -1.8138

Max Act: 1.7035. Min Act: -0.0000

Data Index: 477523 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 1.8138. Min Range: -1.8138

Max Act: 1.4468. Min Act: -0.0000

Data Index: 1125033 (C4 (Web Text))

Max Activating Token Index: 502

Text #3

Max Range: 1.8138. Min Range: -1.8138

Max Act: 1.5376. Min Act: -0.0000

Data Index: 767069 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 1.8138. Min Range: -1.8138

Max Act: 1.4145. Min Act: -0.0000

Data Index: 668002 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 1.8138. Min Range: -1.8138

Max Act: 1.4084. Min Act: -0.0000

Data Index: 226134 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 1.8138. Min Range: -1.8138

Max Act: 1.4070. Min Act: -0.0000

Data Index: 787168 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 1.8138. Min Range: -1.8138

Max Act: 1.3760. Min Act: -0.0000

Data Index: 1256324 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 1.8138. Min Range: -1.8138

Max Act: 1.3903. Min Act: -0.0000

Data Index: 532028 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 1.8138. Min Range: -1.8138

Max Act: 1.3552. Min Act: -0.0000

Data Index: 624671 (C4 (Web Text))

Max Activating Token Index: 655

Text #10

Max Range: 1.8138. Min Range: -1.8138

Max Act: 1.3446. Min Act: -0.0000

Data Index: 1328864 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 1.8138. Min Range: -1.8138

Max Act: 1.4461. Min Act: -0.0000

Data Index: 12478 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 1.8138. Min Range: -1.8138

Max Act: 1.3045. Min Act: -0.0000

Data Index: 1572671 (Python Code)

Max Activating Token Index: 140

Text #13

Max Range: 1.8138. Min Range: -1.8138

Max Act: 1.2936. Min Act: -0.0000

Data Index: 954707 (C4 (Web Text))

Max Activating Token Index: 748

Text #14

Max Range: 1.8138. Min Range: -1.8138

Max Act: 1.2582. Min Act: -0.0000

Data Index: 958090 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 1.8138. Min Range: -1.8138

Max Act: 1.3144. Min Act: -0.0000

Data Index: 261709 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 1.8138. Min Range: -1.8138

Max Act: 1.2560. Min Act: -0.0000

Data Index: 1137320 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 1.8138. Min Range: -1.8138

Max Act: 1.1743. Min Act: -0.0000

Data Index: 241429 (C4 (Web Text))

Max Activating Token Index: 927

Text #18

Max Range: 1.8138. Min Range: -1.8138

Max Act: 1.1405. Min Act: -0.0000

Data Index: 725126 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 1.8138. Min Range: -1.8138

Max Act: 1.3055. Min Act: -0.0000

Data Index: 908188 (C4 (Web Text))

Max Activating Token Index: 978