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

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

Neuron 4256 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2931. Min Range: -2.2931

Max Act: 2.2931. Min Act: -0.0000

Data Index: 947444 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 2.2931. Min Range: -2.2931

Max Act: 2.2336. Min Act: -0.0000

Data Index: 105568 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 2.2931. Min Range: -2.2931

Max Act: 1.8503. Min Act: -0.0000

Data Index: 380766 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 2.2931. Min Range: -2.2931

Max Act: 1.9499. Min Act: -0.0000

Data Index: 461544 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 2.2931. Min Range: -2.2931

Max Act: 2.0571. Min Act: -0.0000

Data Index: 731532 (C4 (Web Text))

Max Activating Token Index: 89

Text #5

Max Range: 2.2931. Min Range: -2.2931

Max Act: 1.8653. Min Act: -0.0000

Data Index: 95483 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 2.2931. Min Range: -2.2931

Max Act: 1.8557. Min Act: -0.0000

Data Index: 971610 (C4 (Web Text))

Max Activating Token Index: 789

Text #7

Max Range: 2.2931. Min Range: -2.2931

Max Act: 1.6994. Min Act: -0.0000

Data Index: 407183 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 2.2931. Min Range: -2.2931

Max Act: 1.6628. Min Act: -0.0000

Data Index: 367438 (C4 (Web Text))

Max Activating Token Index: 804

Text #9

Max Range: 2.2931. Min Range: -2.2931

Max Act: 1.7474. Min Act: -0.0000

Data Index: 754472 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 2.2931. Min Range: -2.2931

Max Act: 1.7111. Min Act: -0.0000

Data Index: 1354978 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 2.2931. Min Range: -2.2931

Max Act: 1.6926. Min Act: -0.0000

Data Index: 1132663 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 2.2931. Min Range: -2.2931

Max Act: 1.6754. Min Act: -0.0000

Data Index: 228792 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 2.2931. Min Range: -2.2931

Max Act: 1.7443. Min Act: -0.0000

Data Index: 916623 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 2.2931. Min Range: -2.2931

Max Act: 1.7283. Min Act: -0.0000

Data Index: 599840 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 2.2931. Min Range: -2.2931

Max Act: 1.7132. Min Act: -0.0000

Data Index: 373621 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 2.2931. Min Range: -2.2931

Max Act: 1.5883. Min Act: 0.0000

Data Index: 1165074 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 2.2931. Min Range: -2.2931

Max Act: 1.6842. Min Act: -0.0000

Data Index: 1117005 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 2.2931. Min Range: -2.2931

Max Act: 1.6745. Min Act: -0.0000

Data Index: 802830 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 2.2931. Min Range: -2.2931

Max Act: 1.6349. Min Act: -0.0000

Data Index: 158024 (C4 (Web Text))

Max Activating Token Index: 570