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

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

Neuron 2742 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2925. Min Range: -1.2925

Max Act: 1.2925. Min Act: -0.0000

Data Index: 1013172 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 1.2925. Min Range: -1.2925

Max Act: 1.0949. Min Act: -0.0000

Data Index: 105275 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 1.2925. Min Range: -1.2925

Max Act: 1.2177. Min Act: -0.0000

Data Index: 950838 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.9790. Min Act: -0.0000

Data Index: 547324 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 1.2925. Min Range: -1.2925

Max Act: 1.0651. Min Act: -0.0000

Data Index: 1303911 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.9507. Min Act: -0.0000

Data Index: 123841 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.9998. Min Act: -0.0000

Data Index: 627362 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.9516. Min Act: -0.0000

Data Index: 1225107 (C4 (Web Text))

Max Activating Token Index: 476

Text #8

Max Range: 1.2925. Min Range: -1.2925

Max Act: 1.0334. Min Act: -0.0000

Data Index: 947081 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.9748. Min Act: -0.0000

Data Index: 209302 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.8789. Min Act: -0.0000

Data Index: 934280 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.8358. Min Act: -0.0000

Data Index: 400702 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.9673. Min Act: -0.0000

Data Index: 616118 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.9078. Min Act: -0.0000

Data Index: 328643 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.9058. Min Act: -0.0000

Data Index: 735104 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.8399. Min Act: -0.0000

Data Index: 84855 (C4 (Web Text))

Max Activating Token Index: 306

Text #16

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.8404. Min Act: -0.0000

Data Index: 1642191 (Python Code)

Max Activating Token Index: 706

Text #17

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.8443. Min Act: -0.0000

Data Index: 1224356 (C4 (Web Text))

Max Activating Token Index: 764

Text #18

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.8326. Min Act: -0.0000

Data Index: 785233 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 1.2925. Min Range: -1.2925

Max Act: 0.8329. Min Act: -0.0000

Data Index: 1301034 (C4 (Web Text))

Max Activating Token Index: 835