Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 55 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.6175. Min Act: -0.0000

Data Index: 308484 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.5070. Min Act: -0.0000

Data Index: 965139 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.4918. Min Act: -0.0000

Data Index: 646931 (C4 (Web Text))

Max Activating Token Index: 542

Text #3

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.4830. Min Act: -0.0000

Data Index: 519336 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.4389. Min Act: -0.0000

Data Index: 654 (C4 (Web Text))

Max Activating Token Index: 919

Text #5

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.4114. Min Act: -0.0000

Data Index: 300456 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.4319. Min Act: -0.0000

Data Index: 864169 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.3850. Min Act: -0.0000

Data Index: 595634 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.3589. Min Act: -0.0000

Data Index: 28537 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.4615. Min Act: -0.0000

Data Index: 1357586 (C4 (Web Text))

Max Activating Token Index: 349

Text #10

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.3884. Min Act: -0.0000

Data Index: 529105 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.3470. Min Act: -0.0000

Data Index: 269981 (C4 (Web Text))

Max Activating Token Index: 345

Text #12

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.3386. Min Act: -0.0000

Data Index: 957583 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.2990. Min Act: -0.0000

Data Index: 684042 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.3066. Min Act: -0.0000

Data Index: 582050 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.3123. Min Act: -0.0000

Data Index: 1254401 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.3201. Min Act: -0.0000

Data Index: 1231457 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.3140. Min Act: -0.0000

Data Index: 674007 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.2585. Min Act: -0.0000

Data Index: 1047935 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.2930. Min Act: -0.0000

Data Index: 779725 (C4 (Web Text))

Max Activating Token Index: 803