Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 2603 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 0.3375. Min Range: -0.3375
Max Act: 0.3375. Min Act: -0.0001
Data Index: 1896912 (The Pile)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.3375. Min Range: -0.3375
Max Act: 0.2733. Min Act: -0.0001
Data Index: 1487964 (The Pile)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.3375. Min Range: -0.3375
Max Act: 0.2589. Min Act: -0.0001
Data Index: 362151 (The Pile)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.3375. Min Range: -0.3375
Max Act: 0.2327. Min Act: -0.0001
Data Index: 1797531 (The Pile)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.3375. Min Range: -0.3375
Max Act: 0.2233. Min Act: -0.0001
Data Index: 358468 (The Pile)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.3375. Min Range: -0.3375
Max Act: 0.2055. Min Act: -0.0001
Data Index: 112172 (The Pile)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.3375. Min Range: -0.3375
Max Act: 0.1920. Min Act: -0.0001
Data Index: 913693 (The Pile)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.3375. Min Range: -0.3375
Max Act: 0.1943. Min Act: -0.0001
Data Index: 63752 (The Pile)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.3375. Min Range: -0.3375
Max Act: 0.1858. Min Act: -0.0001
Data Index: 1547828 (The Pile)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.3375. Min Range: -0.3375
Max Act: 0.1810. Min Act: -0.0001
Data Index: 321269 (The Pile)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.3375. Min Range: -0.3375
Max Act: 0.1918. Min Act: -0.0001
Data Index: 636905 (The Pile)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.3375. Min Range: -0.3375
Max Act: 0.1693. Min Act: -0.0001
Data Index: 709697 (The Pile)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.3375. Min Range: -0.3375
Max Act: 0.1678. Min Act: -0.0001
Data Index: 744532 (The Pile)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.3375. Min Range: -0.3375
Max Act: 0.1744. Min Act: -0.0001
Data Index: 758375 (The Pile)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.3375. Min Range: -0.3375
Max Act: 0.1618. Min Act: -0.0001
Data Index: 284135 (The Pile)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.3375. Min Range: -0.3375
Max Act: 0.1638. Min Act: -0.0001
Data Index: 1050059 (The Pile)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.3375. Min Range: -0.3375
Max Act: 0.1622. Min Act: -0.0001
Data Index: 1602559 (The Pile)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.3375. Min Range: -0.3375
Max Act: 0.1650. Min Act: -0.0001
Data Index: 718411 (The Pile)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.3375. Min Range: -0.3375
Max Act: 0.1636. Min Act: -0.0001
Data Index: 68990 (The Pile)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.3375. Min Range: -0.3375
Max Act: 0.1627. Min Act: -0.0001
Data Index: 335815 (The Pile)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19