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

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

Neuron 63 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.5346. Min Act: -0.0001

Data Index: 1236057 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.5320. Min Act: -0.0002

Data Index: 75600 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.5492. Min Act: -0.0002

Data Index: 162399 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.5176. Min Act: -0.0001

Data Index: 712863 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.4457. Min Act: -0.0001

Data Index: 1261255 (C4 (Web Text))

Max Activating Token Index: 41

Text #5

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.4067. Min Act: -0.0001

Data Index: 914638 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.4123. Min Act: -0.0001

Data Index: 1626780 (Python Code)

Max Activating Token Index: 555

Text #7

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.4122. Min Act: -0.0001

Data Index: 1267170 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.3882. Min Act: -0.0002

Data Index: 893935 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.3875. Min Act: -0.0002

Data Index: 386784 (C4 (Web Text))

Max Activating Token Index: 529

Text #10

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.3780. Min Act: -0.0002

Data Index: 483532 (C4 (Web Text))

Max Activating Token Index: 512

Text #11

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.3618. Min Act: -0.0002

Data Index: 841643 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.3574. Min Act: -0.0001

Data Index: 1542058 (Python Code)

Max Activating Token Index: 141

Text #13

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.3645. Min Act: -0.0001

Data Index: 74890 (C4 (Web Text))

Max Activating Token Index: 951

Text #14

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.3547. Min Act: -0.0001

Data Index: 610959 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.3640. Min Act: -0.0002

Data Index: 488139 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.3700. Min Act: -0.0001

Data Index: 187470 (C4 (Web Text))

Max Activating Token Index: 947

Text #17

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.3462. Min Act: -0.0001

Data Index: 935801 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.3682. Min Act: -0.0001

Data Index: 667485 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 0.5492. Min Range: -0.5492

Max Act: 0.3822. Min Act: -0.0002

Data Index: 304402 (C4 (Web Text))

Max Activating Token Index: 896