Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3624 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8717. Min Range: -0.8717

Max Act: 0.8717. Min Act: -0.0000

Data Index: 1330331 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 0.8717. Min Range: -0.8717

Max Act: 0.8003. Min Act: -0.0000

Data Index: 550148 (C4 (Web Text))

Max Activating Token Index: 591

Text #2

Max Range: 0.8717. Min Range: -0.8717

Max Act: 0.7601. Min Act: -0.0000

Data Index: 1004609 (C4 (Web Text))

Max Activating Token Index: 718

Text #3

Max Range: 0.8717. Min Range: -0.8717

Max Act: 0.6530. Min Act: -0.0001

Data Index: 813288 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 0.8717. Min Range: -0.8717

Max Act: 0.6247. Min Act: -0.0001

Data Index: 694239 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 0.8717. Min Range: -0.8717

Max Act: 0.5805. Min Act: -0.0000

Data Index: 667469 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 0.8717. Min Range: -0.8717

Max Act: 0.6210. Min Act: -0.0000

Data Index: 1152596 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 0.8717. Min Range: -0.8717

Max Act: 0.5942. Min Act: -0.0000

Data Index: 564250 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 0.8717. Min Range: -0.8717

Max Act: 0.6053. Min Act: -0.0000

Data Index: 1228418 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 0.8717. Min Range: -0.8717

Max Act: 0.5609. Min Act: -0.0000

Data Index: 715206 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 0.8717. Min Range: -0.8717

Max Act: 0.5800. Min Act: -0.0001

Data Index: 795227 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 0.8717. Min Range: -0.8717

Max Act: 0.5804. Min Act: -0.0000

Data Index: 651881 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 0.8717. Min Range: -0.8717

Max Act: 0.5877. Min Act: -0.0001

Data Index: 148909 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 0.8717. Min Range: -0.8717

Max Act: 0.5646. Min Act: -0.0000

Data Index: 763628 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 0.8717. Min Range: -0.8717

Max Act: 0.5577. Min Act: -0.0000

Data Index: 591930 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 0.8717. Min Range: -0.8717

Max Act: 0.5142. Min Act: -0.0000

Data Index: 224531 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.8717. Min Range: -0.8717

Max Act: 0.5091. Min Act: -0.0000

Data Index: 617042 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.8717. Min Range: -0.8717

Max Act: 0.5044. Min Act: -0.0001

Data Index: 167663 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.8717. Min Range: -0.8717

Max Act: 0.5341. Min Act: -0.0001

Data Index: 154026 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 0.8717. Min Range: -0.8717

Max Act: 0.5109. Min Act: -0.0000

Data Index: 326082 (C4 (Web Text))

Max Activating Token Index: 805