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

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

Neuron 3738 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.5171. Min Act: -0.0000

Data Index: 960820 (C4 (Web Text))

Max Activating Token Index: 36

Text #1

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.4297. Min Act: -0.0000

Data Index: 259983 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.4840. Min Act: -0.0000

Data Index: 1215133 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.3443. Min Act: -0.0000

Data Index: 564897 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.4046. Min Act: -0.0000

Data Index: 1059412 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.3610. Min Act: -0.0000

Data Index: 146961 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.3587. Min Act: -0.0000

Data Index: 24763 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.3452. Min Act: -0.0000

Data Index: 928701 (C4 (Web Text))

Max Activating Token Index: 214

Text #8

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.3547. Min Act: -0.0000

Data Index: 1277412 (C4 (Web Text))

Max Activating Token Index: 836

Text #9

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.3125. Min Act: -0.0000

Data Index: 634170 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.2990. Min Act: -0.0000

Data Index: 708612 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.2958. Min Act: -0.0000

Data Index: 178398 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.2971. Min Act: -0.0000

Data Index: 726762 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.2563. Min Act: -0.0000

Data Index: 473908 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.2902. Min Act: -0.0000

Data Index: 718541 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.2814. Min Act: -0.0000

Data Index: 1049915 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.2487. Min Act: -0.0000

Data Index: 1007231 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.2770. Min Act: -0.0000

Data Index: 311480 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.2599. Min Act: -0.0000

Data Index: 565201 (C4 (Web Text))

Max Activating Token Index: 856

Text #19

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.2585. Min Act: -0.0000

Data Index: 1106968 (C4 (Web Text))

Max Activating Token Index: 536