Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1220 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.0744. Min Range: -2.0744
Max Act: 1.6915. Min Act: -0.0000
Data Index: 167152 (The Pile)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0744. Min Range: -2.0744
Max Act: 1.7058. Min Act: -0.0000
Data Index: 544355 (The Pile)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0744. Min Range: -2.0744
Max Act: 1.5760. Min Act: -0.0000
Data Index: 905508 (The Pile)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0744. Min Range: -2.0744
Max Act: 1.8479. Min Act: -0.0000
Data Index: 1074733 (The Pile)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0744. Min Range: -2.0744
Max Act: 2.0744. Min Act: -0.0000
Data Index: 1255417 (The Pile)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0744. Min Range: -2.0744
Max Act: 1.4866. Min Act: -0.0000
Data Index: 696713 (The Pile)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0744. Min Range: -2.0744
Max Act: 1.6641. Min Act: -0.0000
Data Index: 352291 (The Pile)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0744. Min Range: -2.0744
Max Act: 1.4706. Min Act: -0.0000
Data Index: 1990191 (The Pile)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0744. Min Range: -2.0744
Max Act: 1.5183. Min Act: -0.0000
Data Index: 1394427 (The Pile)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0744. Min Range: -2.0744
Max Act: 1.5946. Min Act: -0.0000
Data Index: 1795117 (The Pile)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0744. Min Range: -2.0744
Max Act: 1.5554. Min Act: -0.0000
Data Index: 1984040 (The Pile)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0744. Min Range: -2.0744
Max Act: 1.3904. Min Act: -0.0000
Data Index: 1723455 (The Pile)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0744. Min Range: -2.0744
Max Act: 1.1719. Min Act: -0.0000
Data Index: 893311 (The Pile)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0744. Min Range: -2.0744
Max Act: 1.2489. Min Act: -0.0000
Data Index: 1683257 (The Pile)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0744. Min Range: -2.0744
Max Act: 1.6345. Min Act: -0.0000
Data Index: 6164 (The Pile)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0744. Min Range: -2.0744
Max Act: 1.3577. Min Act: -0.0001
Data Index: 399492 (The Pile)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0744. Min Range: -2.0744
Max Act: 1.4178. Min Act: -0.0000
Data Index: 167269 (The Pile)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0744. Min Range: -2.0744
Max Act: 1.5133. Min Act: -0.0000
Data Index: 482707 (The Pile)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0744. Min Range: -2.0744
Max Act: 1.3365. Min Act: -0.0000
Data Index: 25025 (The Pile)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0744. Min Range: -2.0744
Max Act: 1.3262. Min Act: -0.0000
Data Index: 1736614 (The Pile)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #19