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

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

Neuron 5614 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.6186. Min Act: -0.0000

Data Index: 1207116 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.5107. Min Act: -0.0000

Data Index: 430427 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.5366. Min Act: -0.0000

Data Index: 1294216 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.5293. Min Act: -0.0000

Data Index: 131776 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4790. Min Act: -0.0000

Data Index: 445367 (C4 (Web Text))

Max Activating Token Index: 104

Text #5

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4695. Min Act: -0.0000

Data Index: 314662 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4446. Min Act: -0.0000

Data Index: 1151945 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4476. Min Act: -0.0000

Data Index: 307594 (C4 (Web Text))

Max Activating Token Index: 600

Text #8

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4305. Min Act: -0.0000

Data Index: 899214 (C4 (Web Text))

Max Activating Token Index: 712

Text #9

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4100. Min Act: -0.0000

Data Index: 775734 (C4 (Web Text))

Max Activating Token Index: 823

Text #10

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4223. Min Act: -0.0000

Data Index: 1170072 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4315. Min Act: -0.0000

Data Index: 940995 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4088. Min Act: -0.0000

Data Index: 877493 (C4 (Web Text))

Max Activating Token Index: 119

Text #13

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4349. Min Act: -0.0000

Data Index: 97097 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.3983. Min Act: -0.0000

Data Index: 1266822 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.3863. Min Act: -0.0000

Data Index: 1180474 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.3845. Min Act: -0.0000

Data Index: 1332760 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.3803. Min Act: -0.0000

Data Index: 947700 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4079. Min Act: -0.0000

Data Index: 1339663 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.3802. Min Act: -0.0000

Data Index: 523738 (C4 (Web Text))

Max Activating Token Index: 406