Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2180 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.2539. Min Range: -2.2539
Max Act: 2.2539. Min Act: -0.0000
Data Index: 1800840 (The Pile)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2539. Min Range: -2.2539
Max Act: 1.9505. Min Act: -0.0000
Data Index: 734655 (The Pile)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2539. Min Range: -2.2539
Max Act: 2.1142. Min Act: -0.0000
Data Index: 1615376 (The Pile)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2539. Min Range: -2.2539
Max Act: 1.9810. Min Act: -0.0000
Data Index: 406247 (The Pile)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2539. Min Range: -2.2539
Max Act: 2.0341. Min Act: -0.0000
Data Index: 465602 (The Pile)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2539. Min Range: -2.2539
Max Act: 2.1565. Min Act: -0.0000
Data Index: 1319735 (The Pile)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2539. Min Range: -2.2539
Max Act: 2.1118. Min Act: -0.0000
Data Index: 857161 (The Pile)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2539. Min Range: -2.2539
Max Act: 1.8459. Min Act: -0.0000
Data Index: 783854 (The Pile)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2539. Min Range: -2.2539
Max Act: 1.8724. Min Act: -0.0000
Data Index: 758868 (The Pile)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2539. Min Range: -2.2539
Max Act: 1.8590. Min Act: -0.0000
Data Index: 957176 (The Pile)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2539. Min Range: -2.2539
Max Act: 1.8445. Min Act: -0.0000
Data Index: 1460335 (The Pile)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2539. Min Range: -2.2539
Max Act: 1.8297. Min Act: -0.0000
Data Index: 1339499 (The Pile)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2539. Min Range: -2.2539
Max Act: 1.8309. Min Act: -0.0000
Data Index: 179498 (The Pile)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2539. Min Range: -2.2539
Max Act: 1.7362. Min Act: -0.0000
Data Index: 1060155 (The Pile)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2539. Min Range: -2.2539
Max Act: 1.9138. Min Act: -0.0000
Data Index: 1150461 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2539. Min Range: -2.2539
Max Act: 1.8081. Min Act: -0.0000
Data Index: 1490416 (The Pile)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2539. Min Range: -2.2539
Max Act: 1.8037. Min Act: -0.0000
Data Index: 1234048 (The Pile)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2539. Min Range: -2.2539
Max Act: 1.7466. Min Act: -0.0000
Data Index: 426969 (The Pile)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2539. Min Range: -2.2539
Max Act: 1.7154. Min Act: -0.0000
Data Index: 1317070 (The Pile)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2539. Min Range: -2.2539
Max Act: 1.5919. Min Act: -0.0000
Data Index: 58359 (The Pile)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19