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

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

Neuron 3422 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.7089. Min Act: -0.0000

Data Index: 612429 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.5660. Min Act: -0.0000

Data Index: 982213 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.5112. Min Act: -0.0000

Data Index: 959007 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.4499. Min Act: -0.0000

Data Index: 248684 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.4429. Min Act: -0.0000

Data Index: 192194 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1164752 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.4376. Min Act: -0.0000

Data Index: 619580 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.4784. Min Act: -0.0000

Data Index: 159952 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.4346. Min Act: -0.0000

Data Index: 917690 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.4233. Min Act: -0.0000

Data Index: 949885 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.4187. Min Act: -0.0000

Data Index: 1337177 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.4408. Min Act: -0.0000

Data Index: 288962 (C4 (Web Text))

Max Activating Token Index: 319

Text #12

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.3953. Min Act: -0.0000

Data Index: 431833 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.4183. Min Act: -0.0000

Data Index: 439199 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.4081. Min Act: -0.0000

Data Index: 1047117 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.3874. Min Act: -0.0000

Data Index: 1228265 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.4032. Min Act: -0.0000

Data Index: 61026 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.4074. Min Act: -0.0000

Data Index: 969826 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.3754. Min Act: -0.0000

Data Index: 954541 (C4 (Web Text))

Max Activating Token Index: 457

Text #19

Max Range: 0.7089. Min Range: -0.7089

Max Act: 0.4163. Min Act: -0.0000

Data Index: 936642 (C4 (Web Text))

Max Activating Token Index: 408