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

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

Neuron 175 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.8996. Min Act: -0.0000

Data Index: 197125 (C4 (Web Text))

Max Activating Token Index: 686

Text #1

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.8851. Min Act: -0.0000

Data Index: 377340 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.8996. Min Act: -0.0000

Data Index: 1162283 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7815. Min Act: -0.0000

Data Index: 68184 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.8453. Min Act: -0.0000

Data Index: 344661 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7797. Min Act: -0.0000

Data Index: 891949 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.9567. Min Act: -0.0000

Data Index: 247314 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.8430. Min Act: -0.0000

Data Index: 981303 (C4 (Web Text))

Max Activating Token Index: 126

Text #8

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7933. Min Act: -0.0000

Data Index: 908728 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.8460. Min Act: -0.0000

Data Index: 695498 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7215. Min Act: -0.0000

Data Index: 911102 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7288. Min Act: -0.0000

Data Index: 802940 (C4 (Web Text))

Max Activating Token Index: 351

Text #12

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.5768. Min Act: -0.0000

Data Index: 630780 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6657. Min Act: -0.0000

Data Index: 151763 (C4 (Web Text))

Max Activating Token Index: 195

Text #14

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6157. Min Act: -0.0000

Data Index: 1148987 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.7093. Min Act: -0.0000

Data Index: 1203330 (C4 (Web Text))

Max Activating Token Index: 921

Text #16

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6848. Min Act: -0.0000

Data Index: 243921 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6106. Min Act: -0.0000

Data Index: 1541326 (Python Code)

Max Activating Token Index: 533

Text #18

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6051. Min Act: -0.0000

Data Index: 974407 (C4 (Web Text))

Max Activating Token Index: 801

Text #19

Max Range: 0.9567. Min Range: -0.9567

Max Act: 0.6535. Min Act: -0.0000

Data Index: 265580 (C4 (Web Text))

Max Activating Token Index: 990