Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2073 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.3023. Min Range: -2.3023
Max Act: 2.3023. Min Act: 0.0000
Data Index: 659710 (The Pile)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3023. Min Range: -2.3023
Max Act: 2.0945. Min Act: -0.0000
Data Index: 1534686 (The Pile)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3023. Min Range: -2.3023
Max Act: 1.9782. Min Act: 0.0000
Data Index: 474460 (The Pile)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3023. Min Range: -2.3023
Max Act: 1.9441. Min Act: -0.0000
Data Index: 597572 (The Pile)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3023. Min Range: -2.3023
Max Act: 1.9053. Min Act: -0.0000
Data Index: 141547 (The Pile)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3023. Min Range: -2.3023
Max Act: 1.8111. Min Act: -0.0000
Data Index: 98041 (The Pile)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3023. Min Range: -2.3023
Max Act: 1.9207. Min Act: -0.0000
Data Index: 186304 (The Pile)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3023. Min Range: -2.3023
Max Act: 1.7999. Min Act: -0.0000
Data Index: 1525981 (The Pile)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3023. Min Range: -2.3023
Max Act: 1.9951. Min Act: -0.0000
Data Index: 195613 (The Pile)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3023. Min Range: -2.3023
Max Act: 1.9767. Min Act: -0.0000
Data Index: 1436278 (The Pile)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3023. Min Range: -2.3023
Max Act: 1.8496. Min Act: -0.0000
Data Index: 672652 (The Pile)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3023. Min Range: -2.3023
Max Act: 2.0056. Min Act: -0.0000
Data Index: 1646466 (The Pile)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3023. Min Range: -2.3023
Max Act: 1.6161. Min Act: -0.0000
Data Index: 320570 (The Pile)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3023. Min Range: -2.3023
Max Act: 1.8782. Min Act: -0.0000
Data Index: 936983 (The Pile)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3023. Min Range: -2.3023
Max Act: 1.7544. Min Act: 0.0000
Data Index: 1052537 (The Pile)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3023. Min Range: -2.3023
Max Act: 1.6363. Min Act: -0.0000
Data Index: 984652 (The Pile)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3023. Min Range: -2.3023
Max Act: 1.5964. Min Act: -0.0000
Data Index: 1923788 (The Pile)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3023. Min Range: -2.3023
Max Act: 1.7150. Min Act: -0.0000
Data Index: 1384860 (The Pile)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3023. Min Range: -2.3023
Max Act: 1.7127. Min Act: -0.0000
Data Index: 1169638 (The Pile)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3023. Min Range: -2.3023
Max Act: 1.6914. Min Act: 0.0000
Data Index: 1311576 (The Pile)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19