Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 78 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.2012. Min Range: -0.2012
Max Act: 0.2012. Min Act: -0.0001
Data Index: 1814284 (The Pile)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2012. Min Range: -0.2012
Max Act: 0.1670. Min Act: -0.0001
Data Index: 1970561 (The Pile)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2012. Min Range: -0.2012
Max Act: 0.1677. Min Act: -0.0001
Data Index: 1970621 (The Pile)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2012. Min Range: -0.2012
Max Act: 0.1545. Min Act: -0.0001
Data Index: 1512349 (The Pile)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2012. Min Range: -0.2012
Max Act: 0.1695. Min Act: -0.0001
Data Index: 1036003 (The Pile)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2012. Min Range: -0.2012
Max Act: 0.1639. Min Act: -0.0001
Data Index: 235767 (The Pile)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2012. Min Range: -0.2012
Max Act: 0.1526. Min Act: -0.0001
Data Index: 1439819 (The Pile)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2012. Min Range: -0.2012
Max Act: 0.1544. Min Act: -0.0001
Data Index: 231055 (The Pile)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2012. Min Range: -0.2012
Max Act: 0.1575. Min Act: -0.0001
Data Index: 1130656 (The Pile)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2012. Min Range: -0.2012
Max Act: 0.1529. Min Act: -0.0001
Data Index: 251604 (The Pile)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2012. Min Range: -0.2012
Max Act: 0.1529. Min Act: -0.0001
Data Index: 1165498 (The Pile)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2012. Min Range: -0.2012
Max Act: 0.1489. Min Act: -0.0001
Data Index: 1108563 (The Pile)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2012. Min Range: -0.2012
Max Act: 0.1533. Min Act: -0.0001
Data Index: 1080203 (The Pile)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2012. Min Range: -0.2012
Max Act: 0.1658. Min Act: -0.0001
Data Index: 965794 (The Pile)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2012. Min Range: -0.2012
Max Act: 0.1463. Min Act: -0.0001
Data Index: 194391 (The Pile)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2012. Min Range: -0.2012
Max Act: 0.1403. Min Act: -0.0001
Data Index: 1563964 (The Pile)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2012. Min Range: -0.2012
Max Act: 0.1460. Min Act: -0.0001
Data Index: 624554 (The Pile)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2012. Min Range: -0.2012
Max Act: 0.1509. Min Act: -0.0001
Data Index: 1777969 (The Pile)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2012. Min Range: -0.2012
Max Act: 0.1449. Min Act: -0.0001
Data Index: 759816 (The Pile)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2012. Min Range: -0.2012
Max Act: 0.1528. Min Act: -0.0001
Data Index: 102639 (The Pile)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #19