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

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

Neuron 854 in Layer 1

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: 1.8009. Min Range: -1.8009

Max Act: 1.8009. Min Act: -0.0002

Data Index: 472942 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 1.8009. Min Range: -1.8009

Max Act: 1.8004. Min Act: -0.0002

Data Index: 930609 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 1.8009. Min Range: -1.8009

Max Act: 1.7544. Min Act: -0.0002

Data Index: 1047787 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 1.8009. Min Range: -1.8009

Max Act: 1.7903. Min Act: -0.0002

Data Index: 233832 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 1.8009. Min Range: -1.8009

Max Act: 1.7516. Min Act: -0.0002

Data Index: 939847 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 1.8009. Min Range: -1.8009

Max Act: 1.7372. Min Act: -0.0002

Data Index: 478527 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 1.8009. Min Range: -1.8009

Max Act: 1.6783. Min Act: -0.0002

Data Index: 594713 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 1.8009. Min Range: -1.8009

Max Act: 1.6528. Min Act: -0.0002

Data Index: 944004 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 1.8009. Min Range: -1.8009

Max Act: 1.6895. Min Act: -0.0002

Data Index: 43624 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 1.8009. Min Range: -1.8009

Max Act: 1.7190. Min Act: -0.0002

Data Index: 447443 (C4 (Web Text))

Max Activating Token Index: 1001

Text #10

Max Range: 1.8009. Min Range: -1.8009

Max Act: 1.6871. Min Act: -0.0002

Data Index: 653057 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 1.8009. Min Range: -1.8009

Max Act: 1.7034. Min Act: -0.0002

Data Index: 1243769 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 1.8009. Min Range: -1.8009

Max Act: 1.6630. Min Act: -0.0002

Data Index: 1065058 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 1.8009. Min Range: -1.8009

Max Act: 1.6174. Min Act: -0.0002

Data Index: 1355852 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 1.8009. Min Range: -1.8009

Max Act: 1.6416. Min Act: -0.0002

Data Index: 526878 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 1.8009. Min Range: -1.8009

Max Act: 1.6461. Min Act: -0.0002

Data Index: 1342693 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 1.8009. Min Range: -1.8009

Max Act: 1.6520. Min Act: -0.0002

Data Index: 611758 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 1.8009. Min Range: -1.8009

Max Act: 1.6466. Min Act: -0.0002

Data Index: 622118 (C4 (Web Text))

Max Activating Token Index: 290

Text #18

Max Range: 1.8009. Min Range: -1.8009

Max Act: 1.6612. Min Act: -0.0002

Data Index: 709591 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 1.8009. Min Range: -1.8009

Max Act: 1.6501. Min Act: -0.0003

Data Index: 858154 (C4 (Web Text))

Max Activating Token Index: 36