Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 550 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 2.2431. Min Range: -2.2431
Max Act: 2.2431. Min Act: -0.0000
Data Index: 1076464 (The Pile)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2431. Min Range: -2.2431
Max Act: 2.0281. Min Act: -0.0000
Data Index: 1400964 (The Pile)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2431. Min Range: -2.2431
Max Act: 2.1322. Min Act: -0.0000
Data Index: 1353131 (The Pile)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2431. Min Range: -2.2431
Max Act: 2.1019. Min Act: -0.0000
Data Index: 1555297 (The Pile)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2431. Min Range: -2.2431
Max Act: 2.0519. Min Act: -0.0000
Data Index: 1761280 (The Pile)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2431. Min Range: -2.2431
Max Act: 2.0338. Min Act: -0.0000
Data Index: 329813 (The Pile)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2431. Min Range: -2.2431
Max Act: 2.0340. Min Act: -0.0000
Data Index: 1938755 (The Pile)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2431. Min Range: -2.2431
Max Act: 2.1417. Min Act: -0.0000
Data Index: 1714093 (The Pile)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2431. Min Range: -2.2431
Max Act: 1.9135. Min Act: -0.0000
Data Index: 899183 (The Pile)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2431. Min Range: -2.2431
Max Act: 2.0129. Min Act: -0.0000
Data Index: 1437838 (The Pile)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2431. Min Range: -2.2431
Max Act: 2.1112. Min Act: -0.0000
Data Index: 89357 (The Pile)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2431. Min Range: -2.2431
Max Act: 1.9906. Min Act: -0.0000
Data Index: 1962940 (The Pile)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2431. Min Range: -2.2431
Max Act: 1.8912. Min Act: -0.0000
Data Index: 593945 (The Pile)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2431. Min Range: -2.2431
Max Act: 1.8742. Min Act: -0.0000
Data Index: 220969 (The Pile)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2431. Min Range: -2.2431
Max Act: 1.8577. Min Act: -0.0000
Data Index: 607850 (The Pile)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2431. Min Range: -2.2431
Max Act: 1.9488. Min Act: -0.0000
Data Index: 1592837 (The Pile)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2431. Min Range: -2.2431
Max Act: 2.0676. Min Act: -0.0000
Data Index: 75312 (The Pile)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2431. Min Range: -2.2431
Max Act: 1.8401. Min Act: -0.0000
Data Index: 1714831 (The Pile)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2431. Min Range: -2.2431
Max Act: 1.9355. Min Act: -0.0000
Data Index: 711867 (The Pile)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2431. Min Range: -2.2431
Max Act: 2.0439. Min Act: -0.0000
Data Index: 1694011 (The Pile)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #19