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

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

Neuron 4004 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: 0.3908. Min Range: -0.3908

Max Act: 0.3908. Min Act: -0.0001

Data Index: 385052 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3893. Min Act: -0.0001

Data Index: 113802 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3712. Min Act: -0.0001

Data Index: 738090 (C4 (Web Text))

Max Activating Token Index: 936

Text #3

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3119. Min Act: -0.0001

Data Index: 894569 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3269. Min Act: -0.0000

Data Index: 444148 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3172. Min Act: -0.0000

Data Index: 155720 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3051. Min Act: -0.0001

Data Index: 1317592 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3006. Min Act: -0.0000

Data Index: 132616 (C4 (Web Text))

Max Activating Token Index: 596

Text #8

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3296. Min Act: -0.0001

Data Index: 283112 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3309. Min Act: -0.0001

Data Index: 47588 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3143. Min Act: -0.0000

Data Index: 31636 (C4 (Web Text))

Max Activating Token Index: 548

Text #11

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2876. Min Act: -0.0000

Data Index: 350974 (C4 (Web Text))

Max Activating Token Index: 267

Text #12

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3554. Min Act: -0.0001

Data Index: 1036897 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.3272. Min Act: -0.0000

Data Index: 219838 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2883. Min Act: -0.0000

Data Index: 697324 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2812. Min Act: -0.0000

Data Index: 1353294 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2519. Min Act: -0.0001

Data Index: 1126773 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2497. Min Act: -0.0001

Data Index: 486059 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2992. Min Act: -0.0001

Data Index: 1267081 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.3908. Min Range: -0.3908

Max Act: 0.2409. Min Act: -0.0001

Data Index: 1180301 (C4 (Web Text))

Max Activating Token Index: 632