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

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

Neuron 3641 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0053. Min Act: -0.0003

Data Index: 119006 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0041. Min Act: -0.0003

Data Index: 595091 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0040. Min Act: -0.0003

Data Index: 149952 (C4 (Web Text))

Max Activating Token Index: 932

Text #3

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0039. Min Act: -0.0003

Data Index: 460192 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0041. Min Act: -0.0003

Data Index: 519025 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0038. Min Act: -0.0003

Data Index: 1364589 (Python Code)

Max Activating Token Index: 460

Text #6

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0039. Min Act: -0.0003

Data Index: 1058100 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0039. Min Act: -0.0003

Data Index: 543552 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0036. Min Act: -0.0003

Data Index: 1251740 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0036. Min Act: -0.0003

Data Index: 1066504 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0036. Min Act: -0.0004

Data Index: 1467270 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0036. Min Act: -0.0003

Data Index: 461987 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0036. Min Act: -0.0003

Data Index: 1009236 (C4 (Web Text))

Max Activating Token Index: 432

Text #13

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0041. Min Act: -0.0003

Data Index: 1504450 (Python Code)

Max Activating Token Index: 731

Text #14

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0036. Min Act: -0.0003

Data Index: 1612143 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0035. Min Act: -0.0003

Data Index: 1406799 (Python Code)

Max Activating Token Index: 706

Text #16

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0034. Min Act: -0.0003

Data Index: 452812 (C4 (Web Text))

Max Activating Token Index: 957

Text #17

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0034. Min Act: -0.0003

Data Index: 467912 (C4 (Web Text))

Max Activating Token Index: 769

Text #18

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0035. Min Act: -0.0003

Data Index: 916286 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 0.0053. Min Range: -0.0053

Max Act: 0.0035. Min Act: -0.0003

Data Index: 453854 (C4 (Web Text))

Max Activating Token Index: 708