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

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

Neuron 5989 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: 1.1105. Min Range: -1.1105

Max Act: 1.1105. Min Act: -0.0000

Data Index: 1146033 (C4 (Web Text))

Max Activating Token Index: 253

Text #1

Max Range: 1.1105. Min Range: -1.1105

Max Act: 0.8721. Min Act: -0.0000

Data Index: 1021057 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 1.1105. Min Range: -1.1105

Max Act: 0.8632. Min Act: -0.0000

Data Index: 409628 (C4 (Web Text))

Max Activating Token Index: 977

Text #3

Max Range: 1.1105. Min Range: -1.1105

Max Act: 0.7688. Min Act: -0.0000

Data Index: 944235 (C4 (Web Text))

Max Activating Token Index: 706

Text #4

Max Range: 1.1105. Min Range: -1.1105

Max Act: 0.7870. Min Act: -0.0000

Data Index: 516910 (C4 (Web Text))

Max Activating Token Index: 1001

Text #5

Max Range: 1.1105. Min Range: -1.1105

Max Act: 0.7656. Min Act: -0.0000

Data Index: 787057 (C4 (Web Text))

Max Activating Token Index: 284

Text #6

Max Range: 1.1105. Min Range: -1.1105

Max Act: 0.7619. Min Act: -0.0000

Data Index: 987570 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 1.1105. Min Range: -1.1105

Max Act: 0.7228. Min Act: -0.0000

Data Index: 896200 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 1.1105. Min Range: -1.1105

Max Act: 0.7482. Min Act: -0.0000

Data Index: 482975 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 1.1105. Min Range: -1.1105

Max Act: 0.7512. Min Act: -0.0000

Data Index: 78054 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 1.1105. Min Range: -1.1105

Max Act: 0.7453. Min Act: -0.0000

Data Index: 29993 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 1.1105. Min Range: -1.1105

Max Act: 0.7647. Min Act: -0.0000

Data Index: 1212306 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 1.1105. Min Range: -1.1105

Max Act: 0.7240. Min Act: -0.0000

Data Index: 7523 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 1.1105. Min Range: -1.1105

Max Act: 0.6948. Min Act: -0.0000

Data Index: 1011232 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 1.1105. Min Range: -1.1105

Max Act: 0.7162. Min Act: -0.0000

Data Index: 983536 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 1.1105. Min Range: -1.1105

Max Act: 0.7205. Min Act: -0.0000

Data Index: 764909 (C4 (Web Text))

Max Activating Token Index: 875

Text #16

Max Range: 1.1105. Min Range: -1.1105

Max Act: 0.7080. Min Act: -0.0000

Data Index: 1075006 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 1.1105. Min Range: -1.1105

Max Act: 0.7096. Min Act: -0.0000

Data Index: 95847 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 1.1105. Min Range: -1.1105

Max Act: 0.7064. Min Act: -0.0000

Data Index: 469314 (C4 (Web Text))

Max Activating Token Index: 828

Text #19

Max Range: 1.1105. Min Range: -1.1105

Max Act: 0.6780. Min Act: -0.0000

Data Index: 803821 (C4 (Web Text))

Max Activating Token Index: 376