Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 830 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.2770. Min Act: 0.0000
Data Index: 245980 (The Pile)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.1696. Min Act: -0.0000
Data Index: 1597285 (The Pile)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.1600. Min Act: 0.0001
Data Index: 131752 (The Pile)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.1643. Min Act: 0.0000
Data Index: 1133248 (The Pile)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.1341. Min Act: -0.0000
Data Index: 697072 (The Pile)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.1117. Min Act: -0.0000
Data Index: 1784318 (The Pile)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.0161. Min Act: -0.0000
Data Index: 1613901 (The Pile)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.0259. Min Act: -0.0000
Data Index: 1721674 (The Pile)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.0714. Min Act: -0.0000
Data Index: 167856 (The Pile)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.0652. Min Act: 0.0000
Data Index: 737479 (The Pile)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2770. Min Range: -1.2770
Max Act: 0.9996. Min Act: 0.0000
Data Index: 1824548 (The Pile)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.0596. Min Act: 0.0001
Data Index: 1020566 (The Pile)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2770. Min Range: -1.2770
Max Act: 1.0301. Min Act: 0.0000
Data Index: 75875 (The Pile)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2770. Min Range: -1.2770
Max Act: 0.9764. Min Act: -0.0000
Data Index: 1745063 (The Pile)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2770. Min Range: -1.2770
Max Act: 0.9958. Min Act: 0.0001
Data Index: 1914292 (The Pile)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2770. Min Range: -1.2770
Max Act: 0.9811. Min Act: 0.0001
Data Index: 539818 (The Pile)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2770. Min Range: -1.2770
Max Act: 0.9659. Min Act: 0.0000
Data Index: 70394 (The Pile)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2770. Min Range: -1.2770
Max Act: 0.9683. Min Act: -0.0000
Data Index: 1450667 (The Pile)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2770. Min Range: -1.2770
Max Act: 0.9739. Min Act: -0.0000
Data Index: 733635 (The Pile)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2770. Min Range: -1.2770
Max Act: 0.9608. Min Act: 0.0000
Data Index: 1134930 (The Pile)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19