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

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

Neuron 2431 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.8008. Min Act: -0.0000

Data Index: 757220 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.7174. Min Act: -0.0000

Data Index: 1211353 (C4 (Web Text))

Max Activating Token Index: 147

Text #2

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.6362. Min Act: -0.0000

Data Index: 921193 (C4 (Web Text))

Max Activating Token Index: 143

Text #3

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.6761. Min Act: -0.0000

Data Index: 1096634 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.6901. Min Act: -0.0001

Data Index: 915971 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.6300. Min Act: -0.0000

Data Index: 247474 (C4 (Web Text))

Max Activating Token Index: 83

Text #6

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.6601. Min Act: -0.0000

Data Index: 249274 (C4 (Web Text))

Max Activating Token Index: 196

Text #7

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.5904. Min Act: -0.0000

Data Index: 109569 (C4 (Web Text))

Max Activating Token Index: 257

Text #8

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.5544. Min Act: -0.0000

Data Index: 154794 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.5198. Min Act: -0.0000

Data Index: 1078337 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.4819. Min Act: -0.0000

Data Index: 1190369 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.3565. Min Act: -0.0000

Data Index: 587849 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.4387. Min Act: -0.0000

Data Index: 1095126 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.4942. Min Act: -0.0000

Data Index: 38045 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.4510. Min Act: -0.0000

Data Index: 414453 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.4750. Min Act: -0.0000

Data Index: 314850 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.3857. Min Act: -0.0001

Data Index: 987331 (C4 (Web Text))

Max Activating Token Index: 942

Text #17

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.4150. Min Act: -0.0001

Data Index: 1248889 (C4 (Web Text))

Max Activating Token Index: 544

Text #18

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.3356. Min Act: -0.0000

Data Index: 1258432 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 0.8008. Min Range: -0.8008

Max Act: 0.4841. Min Act: -0.0000

Data Index: 449855 (C4 (Web Text))

Max Activating Token Index: 47