Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 838 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.1919. Min Range: -0.1919
Max Act: 0.1919. Min Act: -0.0001
Data Index: 1369047 (The Pile)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1919. Min Range: -0.1919
Max Act: 0.1746. Min Act: -0.0001
Data Index: 107142 (The Pile)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1919. Min Range: -0.1919
Max Act: 0.1367. Min Act: -0.0001
Data Index: 948811 (The Pile)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1919. Min Range: -0.1919
Max Act: 0.1604. Min Act: -0.0001
Data Index: 641566 (The Pile)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1919. Min Range: -0.1919
Max Act: 0.1848. Min Act: -0.0001
Data Index: 99574 (The Pile)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1919. Min Range: -0.1919
Max Act: 0.1651. Min Act: -0.0001
Data Index: 1411361 (The Pile)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1919. Min Range: -0.1919
Max Act: 0.1228. Min Act: -0.0001
Data Index: 886829 (The Pile)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1919. Min Range: -0.1919
Max Act: 0.1771. Min Act: -0.0001
Data Index: 881119 (The Pile)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1919. Min Range: -0.1919
Max Act: 0.1591. Min Act: -0.0001
Data Index: 43070 (The Pile)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1919. Min Range: -0.1919
Max Act: 0.1374. Min Act: -0.0001
Data Index: 178573 (The Pile)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1919. Min Range: -0.1919
Max Act: 0.1243. Min Act: -0.0001
Data Index: 1090380 (The Pile)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1919. Min Range: -0.1919
Max Act: 0.1364. Min Act: -0.0001
Data Index: 941654 (The Pile)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1919. Min Range: -0.1919
Max Act: 0.1494. Min Act: -0.0001
Data Index: 932453 (The Pile)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1919. Min Range: -0.1919
Max Act: 0.1577. Min Act: -0.0001
Data Index: 1887445 (The Pile)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1919. Min Range: -0.1919
Max Act: 0.1414. Min Act: -0.0001
Data Index: 280205 (The Pile)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1919. Min Range: -0.1919
Max Act: 0.1435. Min Act: -0.0001
Data Index: 667680 (The Pile)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1919. Min Range: -0.1919
Max Act: 0.1768. Min Act: -0.0001
Data Index: 357387 (The Pile)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1919. Min Range: -0.1919
Max Act: 0.1423. Min Act: -0.0001
Data Index: 452754 (The Pile)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1919. Min Range: -0.1919
Max Act: 0.1423. Min Act: -0.0001
Data Index: 559095 (The Pile)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1919. Min Range: -0.1919
Max Act: 0.1323. Min Act: -0.0001
Data Index: 13919 (The Pile)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19