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

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

Neuron 4723 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: 1.1093. Min Range: -1.1093

Max Act: 0.9892. Min Act: -0.0000

Data Index: 771616 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 1.1093. Min Range: -1.1093

Max Act: 1.1093. Min Act: -0.0000

Data Index: 380224 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.8933. Min Act: -0.0000

Data Index: 1257171 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.8582. Min Act: -0.0000

Data Index: 1062675 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.8536. Min Act: -0.0000

Data Index: 945943 (C4 (Web Text))

Max Activating Token Index: 595

Text #5

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.8265. Min Act: -0.0000

Data Index: 12085 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.8988. Min Act: 0.0000

Data Index: 987391 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 1.1093. Min Range: -1.1093

Max Act: 1.0028. Min Act: 0.0000

Data Index: 1472905 (Python Code)

Max Activating Token Index: 803

Text #8

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.8447. Min Act: -0.0000

Data Index: 1070521 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.8652. Min Act: -0.0000

Data Index: 221534 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.7875. Min Act: 0.0001

Data Index: 1137178 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.8691. Min Act: -0.0000

Data Index: 307264 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.7833. Min Act: 0.0000

Data Index: 306731 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.7479. Min Act: -0.0000

Data Index: 940817 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.7754. Min Act: -0.0000

Data Index: 477177 (C4 (Web Text))

Max Activating Token Index: 213

Text #15

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.6516. Min Act: 0.0000

Data Index: 1582872 (Python Code)

Max Activating Token Index: 326

Text #16

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.7152. Min Act: -0.0000

Data Index: 1225727 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.6983. Min Act: -0.0000

Data Index: 32435 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.7325. Min Act: -0.0000

Data Index: 130504 (C4 (Web Text))

Max Activating Token Index: 163

Text #19

Max Range: 1.1093. Min Range: -1.1093

Max Act: 0.7400. Min Act: -0.0000

Data Index: 109048 (C4 (Web Text))

Max Activating Token Index: 741