Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4762 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.3169. Min Range: -1.3169

Max Act: 1.3169. Min Act: -0.0000

Data Index: 805557 (The Pile)

Max Activating Token Index: 605

Text #1

Max Range: 1.3169. Min Range: -1.3169

Max Act: 1.2048. Min Act: -0.0000

Data Index: 950814 (The Pile)

Max Activating Token Index: 380

Text #2

Max Range: 1.3169. Min Range: -1.3169

Max Act: 1.1169. Min Act: -0.0000

Data Index: 1946829 (The Pile)

Max Activating Token Index: 620

Text #3

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.9957. Min Act: -0.0000

Data Index: 187074 (The Pile)

Max Activating Token Index: 477

Text #4

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.9703. Min Act: -0.0000

Data Index: 1466517 (The Pile)

Max Activating Token Index: 775

Text #5

Max Range: 1.3169. Min Range: -1.3169

Max Act: 1.0071. Min Act: -0.0000

Data Index: 143140 (The Pile)

Max Activating Token Index: 762

Text #6

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.9803. Min Act: -0.0000

Data Index: 74339 (The Pile)

Max Activating Token Index: 709

Text #7

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.9434. Min Act: -0.0000

Data Index: 1425396 (The Pile)

Max Activating Token Index: 717

Text #8

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.9329. Min Act: -0.0000

Data Index: 116749 (The Pile)

Max Activating Token Index: 621

Text #9

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.9384. Min Act: -0.0000

Data Index: 1546820 (The Pile)

Max Activating Token Index: 373

Text #10

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.9264. Min Act: -0.0000

Data Index: 1594470 (The Pile)

Max Activating Token Index: 260

Text #11

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.9110. Min Act: -0.0000

Data Index: 1425568 (The Pile)

Max Activating Token Index: 561

Text #12

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.8933. Min Act: -0.0000

Data Index: 1934610 (The Pile)

Max Activating Token Index: 738

Text #13

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.7893. Min Act: -0.0000

Data Index: 1117543 (The Pile)

Max Activating Token Index: 929

Text #14

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.8822. Min Act: -0.0000

Data Index: 1920919 (The Pile)

Max Activating Token Index: 742

Text #15

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.8491. Min Act: -0.0000

Data Index: 1177978 (The Pile)

Max Activating Token Index: 729

Text #16

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.8980. Min Act: -0.0000

Data Index: 1505205 (The Pile)

Max Activating Token Index: 523

Text #17

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.8634. Min Act: -0.0000

Data Index: 1188412 (The Pile)

Max Activating Token Index: 690

Text #18

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.8934. Min Act: -0.0000

Data Index: 165189 (The Pile)

Max Activating Token Index: 905

Text #19

Max Range: 1.3169. Min Range: -1.3169

Max Act: 0.8307. Min Act: -0.0000

Data Index: 1614351 (The Pile)

Max Activating Token Index: 284