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

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

Neuron 1614 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.6952. Min Act: -0.0000

Data Index: 521834 (C4 (Web Text))

Max Activating Token Index: 74

Text #1

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.6972. Min Act: -0.0001

Data Index: 662103 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.6012. Min Act: -0.0001

Data Index: 27942 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.6042. Min Act: -0.0001

Data Index: 1086554 (C4 (Web Text))

Max Activating Token Index: 542

Text #4

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5690. Min Act: -0.0000

Data Index: 1016478 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5569. Min Act: -0.0001

Data Index: 1010616 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5319. Min Act: -0.0001

Data Index: 1053690 (C4 (Web Text))

Max Activating Token Index: 776

Text #7

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5079. Min Act: -0.0000

Data Index: 800251 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5369. Min Act: -0.0001

Data Index: 1130705 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5011. Min Act: -0.0000

Data Index: 1317380 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.4800. Min Act: -0.0000

Data Index: 399969 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.4703. Min Act: -0.0000

Data Index: 1012461 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.5161. Min Act: -0.0000

Data Index: 769235 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.4647. Min Act: -0.0000

Data Index: 1047717 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.4674. Min Act: -0.0001

Data Index: 1349023 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.4473. Min Act: -0.0000

Data Index: 366690 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.4312. Min Act: -0.0000

Data Index: 413686 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.4921. Min Act: -0.0001

Data Index: 884286 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.4568. Min Act: -0.0001

Data Index: 761442 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 0.6972. Min Range: -0.6972

Max Act: 0.4712. Min Act: -0.0000

Data Index: 269399 (C4 (Web Text))

Max Activating Token Index: 300