Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1981 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.9510. Min Range: -1.9510
Max Act: 1.7283. Min Act: -0.0001
Data Index: 98872 (The Pile)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9510. Min Range: -1.9510
Max Act: 1.9510. Min Act: -0.0001
Data Index: 429834 (The Pile)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9510. Min Range: -1.9510
Max Act: 1.6771. Min Act: -0.0001
Data Index: 1667233 (The Pile)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9510. Min Range: -1.9510
Max Act: 1.7184. Min Act: -0.0001
Data Index: 1271910 (The Pile)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9510. Min Range: -1.9510
Max Act: 1.9178. Min Act: -0.0001
Data Index: 572301 (The Pile)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9510. Min Range: -1.9510
Max Act: 1.8120. Min Act: -0.0001
Data Index: 1249922 (The Pile)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9510. Min Range: -1.9510
Max Act: 1.8503. Min Act: -0.0000
Data Index: 1237559 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9510. Min Range: -1.9510
Max Act: 1.7687. Min Act: -0.0001
Data Index: 877574 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9510. Min Range: -1.9510
Max Act: 1.8010. Min Act: -0.0001
Data Index: 17678 (The Pile)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9510. Min Range: -1.9510
Max Act: 1.4971. Min Act: -0.0001
Data Index: 69065 (The Pile)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9510. Min Range: -1.9510
Max Act: 1.6771. Min Act: -0.0001
Data Index: 1743476 (The Pile)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9510. Min Range: -1.9510
Max Act: 1.5691. Min Act: -0.0001
Data Index: 1684258 (The Pile)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9510. Min Range: -1.9510
Max Act: 1.5856. Min Act: -0.0001
Data Index: 1010318 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9510. Min Range: -1.9510
Max Act: 1.6765. Min Act: -0.0001
Data Index: 1864870 (The Pile)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9510. Min Range: -1.9510
Max Act: 1.6679. Min Act: -0.0001
Data Index: 1500541 (The Pile)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9510. Min Range: -1.9510
Max Act: 1.5876. Min Act: -0.0000
Data Index: 1405690 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9510. Min Range: -1.9510
Max Act: 1.6891. Min Act: -0.0001
Data Index: 23738 (The Pile)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9510. Min Range: -1.9510
Max Act: 1.6658. Min Act: -0.0001
Data Index: 436713 (The Pile)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9510. Min Range: -1.9510
Max Act: 1.7235. Min Act: -0.0000
Data Index: 277234 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9510. Min Range: -1.9510
Max Act: 1.6097. Min Act: -0.0001
Data Index: 173543 (The Pile)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #19