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

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

Neuron 2970 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.5277. Min Act: -0.0001

Data Index: 346858 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.5208. Min Act: -0.0001

Data Index: 1016059 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.5198. Min Act: -0.0001

Data Index: 985111 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.5095. Min Act: -0.0001

Data Index: 1088654 (C4 (Web Text))

Max Activating Token Index: 119

Text #4

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.5268. Min Act: -0.0001

Data Index: 1174962 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.5024. Min Act: -0.0001

Data Index: 742674 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.5218. Min Act: -0.0001

Data Index: 1340956 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.5130. Min Act: -0.0001

Data Index: 467545 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.5099. Min Act: -0.0001

Data Index: 350801 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.5072. Min Act: -0.0001

Data Index: 1264307 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4889. Min Act: -0.0001

Data Index: 769054 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4894. Min Act: -0.0001

Data Index: 440034 (C4 (Web Text))

Max Activating Token Index: 98

Text #12

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4994. Min Act: -0.0001

Data Index: 832679 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4853. Min Act: -0.0001

Data Index: 349800 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4829. Min Act: -0.0001

Data Index: 520432 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4892. Min Act: -0.0001

Data Index: 560135 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4743. Min Act: -0.0001

Data Index: 1240163 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4929. Min Act: -0.0001

Data Index: 720947 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4951. Min Act: -0.0001

Data Index: 773276 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.5277. Min Range: -0.5277

Max Act: 0.4937. Min Act: -0.0001

Data Index: 953053 (C4 (Web Text))

Max Activating Token Index: 133