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

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

Neuron 4896 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: 3.5198. Min Range: -3.5198

Max Act: 3.5198. Min Act: -0.0000

Data Index: 1024561 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 3.5198. Min Range: -3.5198

Max Act: 3.4819. Min Act: -0.0000

Data Index: 923468 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 3.5198. Min Range: -3.5198

Max Act: 3.2904. Min Act: -0.0000

Data Index: 302986 (C4 (Web Text))

Max Activating Token Index: 661

Text #3

Max Range: 3.5198. Min Range: -3.5198

Max Act: 2.9673. Min Act: -0.0000

Data Index: 1363118 (Python Code)

Max Activating Token Index: 147

Text #4

Max Range: 3.5198. Min Range: -3.5198

Max Act: 2.7032. Min Act: -0.0000

Data Index: 1076696 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 3.5198. Min Range: -3.5198

Max Act: 2.7297. Min Act: -0.0000

Data Index: 1354048 (C4 (Web Text))

Max Activating Token Index: 367

Text #6

Max Range: 3.5198. Min Range: -3.5198

Max Act: 2.7174. Min Act: -0.0000

Data Index: 1354143 (C4 (Web Text))

Max Activating Token Index: 787

Text #7

Max Range: 3.5198. Min Range: -3.5198

Max Act: 2.6962. Min Act: -0.0000

Data Index: 1140906 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 3.5198. Min Range: -3.5198

Max Act: 2.6445. Min Act: -0.0000

Data Index: 108140 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 3.5198. Min Range: -3.5198

Max Act: 2.6516. Min Act: -0.0000

Data Index: 1464970 (Python Code)

Max Activating Token Index: 6

Text #10

Max Range: 3.5198. Min Range: -3.5198

Max Act: 2.7996. Min Act: -0.0000

Data Index: 214914 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 3.5198. Min Range: -3.5198

Max Act: 2.5334. Min Act: -0.0000

Data Index: 991699 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 3.5198. Min Range: -3.5198

Max Act: 2.2730. Min Act: -0.0000

Data Index: 3686 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 3.5198. Min Range: -3.5198

Max Act: 2.3259. Min Act: -0.0000

Data Index: 57937 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 3.5198. Min Range: -3.5198

Max Act: 2.2870. Min Act: -0.0000

Data Index: 1621942 (Python Code)

Max Activating Token Index: 654

Text #15

Max Range: 3.5198. Min Range: -3.5198

Max Act: 2.2499. Min Act: -0.0000

Data Index: 223305 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 3.5198. Min Range: -3.5198

Max Act: 2.2358. Min Act: -0.0000

Data Index: 1432453 (Python Code)

Max Activating Token Index: 356

Text #17

Max Range: 3.5198. Min Range: -3.5198

Max Act: 2.2155. Min Act: -0.0000

Data Index: 1489639 (Python Code)

Max Activating Token Index: 805

Text #18

Max Range: 3.5198. Min Range: -3.5198

Max Act: 2.0177. Min Act: -0.0000

Data Index: 1449281 (Python Code)

Max Activating Token Index: 928

Text #19

Max Range: 3.5198. Min Range: -3.5198

Max Act: 2.0530. Min Act: -0.0000

Data Index: 1453484 (Python Code)

Max Activating Token Index: 223