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

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

Neuron 2659 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1952. Min Range: -2.1952

Max Act: 2.1952. Min Act: -0.0000

Data Index: 360110 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 2.1952. Min Range: -2.1952

Max Act: 1.7971. Min Act: -0.0000

Data Index: 107759 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 2.1952. Min Range: -2.1952

Max Act: 1.6999. Min Act: -0.0000

Data Index: 1142457 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 2.1952. Min Range: -2.1952

Max Act: 1.5049. Min Act: -0.0000

Data Index: 927534 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 2.1952. Min Range: -2.1952

Max Act: 1.4899. Min Act: -0.0000

Data Index: 551977 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 2.1952. Min Range: -2.1952

Max Act: 1.6549. Min Act: -0.0000

Data Index: 1306389 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 2.1952. Min Range: -2.1952

Max Act: 1.4850. Min Act: -0.0000

Data Index: 948052 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 2.1952. Min Range: -2.1952

Max Act: 1.5137. Min Act: -0.0000

Data Index: 868944 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 2.1952. Min Range: -2.1952

Max Act: 1.3587. Min Act: -0.0000

Data Index: 1100902 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 2.1952. Min Range: -2.1952

Max Act: 1.4576. Min Act: -0.0000

Data Index: 396606 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 2.1952. Min Range: -2.1952

Max Act: 1.4339. Min Act: -0.0000

Data Index: 1018366 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 2.1952. Min Range: -2.1952

Max Act: 1.4835. Min Act: -0.0000

Data Index: 64033 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 2.1952. Min Range: -2.1952

Max Act: 1.2439. Min Act: -0.0000

Data Index: 16515 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 2.1952. Min Range: -2.1952

Max Act: 1.4712. Min Act: -0.0000

Data Index: 617820 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 2.1952. Min Range: -2.1952

Max Act: 1.2695. Min Act: -0.0000

Data Index: 641649 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 2.1952. Min Range: -2.1952

Max Act: 1.2439. Min Act: -0.0000

Data Index: 906006 (C4 (Web Text))

Max Activating Token Index: 405

Text #16

Max Range: 2.1952. Min Range: -2.1952

Max Act: 1.2404. Min Act: -0.0000

Data Index: 1357704 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 2.1952. Min Range: -2.1952

Max Act: 1.3120. Min Act: -0.0000

Data Index: 77522 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 2.1952. Min Range: -2.1952

Max Act: 1.2269. Min Act: -0.0000

Data Index: 167755 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 2.1952. Min Range: -2.1952

Max Act: 1.2194. Min Act: -0.0000

Data Index: 911541 (C4 (Web Text))

Max Activating Token Index: 398