Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 690 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.1275. Min Range: -1.1275
Max Act: 1.1275. Min Act: -0.0001
Data Index: 732396 (The Pile)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1275. Min Range: -1.1275
Max Act: 0.9876. Min Act: -0.0001
Data Index: 1121966 (The Pile)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1275. Min Range: -1.1275
Max Act: 0.9943. Min Act: -0.0001
Data Index: 1381783 (The Pile)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1275. Min Range: -1.1275
Max Act: 0.9381. Min Act: -0.0001
Data Index: 1334075 (The Pile)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1275. Min Range: -1.1275
Max Act: 1.0566. Min Act: -0.0001
Data Index: 64077 (The Pile)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1275. Min Range: -1.1275
Max Act: 0.9581. Min Act: -0.0001
Data Index: 1219575 (The Pile)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1275. Min Range: -1.1275
Max Act: 0.8412. Min Act: -0.0002
Data Index: 1812434 (The Pile)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1275. Min Range: -1.1275
Max Act: 0.8538. Min Act: -0.0001
Data Index: 1842491 (The Pile)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1275. Min Range: -1.1275
Max Act: 0.8953. Min Act: -0.0001
Data Index: 765429 (The Pile)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1275. Min Range: -1.1275
Max Act: 0.9534. Min Act: -0.0001
Data Index: 431163 (The Pile)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1275. Min Range: -1.1275
Max Act: 0.8666. Min Act: -0.0001
Data Index: 1525794 (The Pile)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1275. Min Range: -1.1275
Max Act: 0.8047. Min Act: -0.0001
Data Index: 694920 (The Pile)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1275. Min Range: -1.1275
Max Act: 0.7490. Min Act: -0.0001
Data Index: 1805137 (The Pile)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1275. Min Range: -1.1275
Max Act: 0.9192. Min Act: -0.0001
Data Index: 1223861 (The Pile)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1275. Min Range: -1.1275
Max Act: 0.9156. Min Act: -0.0001
Data Index: 1887671 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1275. Min Range: -1.1275
Max Act: 0.8891. Min Act: -0.0001
Data Index: 669571 (The Pile)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1275. Min Range: -1.1275
Max Act: 0.9644. Min Act: -0.0001
Data Index: 914917 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1275. Min Range: -1.1275
Max Act: 0.9133. Min Act: -0.0001
Data Index: 1987829 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1275. Min Range: -1.1275
Max Act: 0.7713. Min Act: -0.0001
Data Index: 1561774 (The Pile)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1275. Min Range: -1.1275
Max Act: 0.8702. Min Act: -0.0001
Data Index: 1786796 (The Pile)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #19