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

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

Neuron 5767 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.7399. Min Act: -0.0001

Data Index: 855265 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.6655. Min Act: -0.0001

Data Index: 344140 (C4 (Web Text))

Max Activating Token Index: 712

Text #2

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.4064. Min Act: -0.0001

Data Index: 806619 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.4947. Min Act: -0.0001

Data Index: 1262392 (C4 (Web Text))

Max Activating Token Index: 391

Text #4

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.4956. Min Act: -0.0001

Data Index: 785698 (C4 (Web Text))

Max Activating Token Index: 113

Text #5

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.1638. Min Act: -0.0001

Data Index: 825899 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.0785. Min Act: -0.0001

Data Index: 1405394 (Python Code)

Max Activating Token Index: 1015

Text #7

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.0939. Min Act: -0.0001

Data Index: 371267 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 1.7399. Min Range: -1.7399

Max Act: 0.9913. Min Act: -0.0001

Data Index: 589453 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 1.7399. Min Range: -1.7399

Max Act: 0.9167. Min Act: -0.0001

Data Index: 1629424 (Python Code)

Max Activating Token Index: 856

Text #10

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.0146. Min Act: -0.0001

Data Index: 574511 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 1.7399. Min Range: -1.7399

Max Act: 0.9352. Min Act: -0.0001

Data Index: 1362053 (Python Code)

Max Activating Token Index: 968

Text #12

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.0073. Min Act: -0.0001

Data Index: 726723 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.0020. Min Act: -0.0001

Data Index: 939808 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 1.7399. Min Range: -1.7399

Max Act: 0.9452. Min Act: -0.0001

Data Index: 1580267 (Python Code)

Max Activating Token Index: 993

Text #15

Max Range: 1.7399. Min Range: -1.7399

Max Act: 0.9058. Min Act: -0.0001

Data Index: 163297 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 1.7399. Min Range: -1.7399

Max Act: 1.0246. Min Act: -0.0001

Data Index: 591450 (C4 (Web Text))

Max Activating Token Index: 914

Text #17

Max Range: 1.7399. Min Range: -1.7399

Max Act: 0.9196. Min Act: -0.0001

Data Index: 1484373 (Python Code)

Max Activating Token Index: 809

Text #18

Max Range: 1.7399. Min Range: -1.7399

Max Act: 0.9610. Min Act: -0.0001

Data Index: 1439059 (Python Code)

Max Activating Token Index: 894

Text #19

Max Range: 1.7399. Min Range: -1.7399

Max Act: 0.9535. Min Act: -0.0001

Data Index: 1341639 (C4 (Web Text))

Max Activating Token Index: 998