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

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

Neuron 1160 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: 0.5993. Min Range: -0.5993

Max Act: 0.5993. Min Act: -0.0000

Data Index: 900667 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.5279. Min Act: -0.0001

Data Index: 1074664 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.4522. Min Act: -0.0000

Data Index: 1107874 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.4686. Min Act: -0.0000

Data Index: 892500 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.4364. Min Act: -0.0000

Data Index: 744781 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.4383. Min Act: -0.0000

Data Index: 542570 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.4418. Min Act: -0.0001

Data Index: 803478 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.4032. Min Act: -0.0000

Data Index: 977938 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.4118. Min Act: -0.0000

Data Index: 1103217 (C4 (Web Text))

Max Activating Token Index: 964

Text #9

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.4241. Min Act: -0.0000

Data Index: 1357032 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.3925. Min Act: -0.0000

Data Index: 1035905 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.4034. Min Act: -0.0001

Data Index: 1064611 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.4015. Min Act: -0.0000

Data Index: 708251 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.4011. Min Act: -0.0000

Data Index: 132578 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.4010. Min Act: -0.0000

Data Index: 388005 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.4007. Min Act: -0.0000

Data Index: 543828 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.3830. Min Act: -0.0000

Data Index: 619862 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.3936. Min Act: -0.0000

Data Index: 338165 (C4 (Web Text))

Max Activating Token Index: 894

Text #18

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.3912. Min Act: -0.0000

Data Index: 1322980 (C4 (Web Text))

Max Activating Token Index: 925

Text #19

Max Range: 0.5993. Min Range: -0.5993

Max Act: 0.3984. Min Act: -0.0001

Data Index: 1091660 (C4 (Web Text))

Max Activating Token Index: 643