Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 1548 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 1.1990. Min Range: -1.1990
Max Act: 1.1920. Min Act: -0.0001
Data Index: 234646 (The Pile)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1990. Min Range: -1.1990
Max Act: 1.1990. Min Act: -0.0001
Data Index: 575523 (The Pile)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1990. Min Range: -1.1990
Max Act: 1.1666. Min Act: -0.0001
Data Index: 297362 (The Pile)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1990. Min Range: -1.1990
Max Act: 1.1133. Min Act: -0.0001
Data Index: 1159992 (The Pile)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1990. Min Range: -1.1990
Max Act: 1.0585. Min Act: -0.0001
Data Index: 1633004 (The Pile)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1990. Min Range: -1.1990
Max Act: 1.0651. Min Act: -0.0001
Data Index: 1639044 (The Pile)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1990. Min Range: -1.1990
Max Act: 1.0866. Min Act: -0.0001
Data Index: 191989 (The Pile)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1990. Min Range: -1.1990
Max Act: 1.0408. Min Act: -0.0001
Data Index: 105132 (The Pile)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1990. Min Range: -1.1990
Max Act: 1.0070. Min Act: -0.0001
Data Index: 1678425 (The Pile)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1990. Min Range: -1.1990
Max Act: 1.0273. Min Act: -0.0001
Data Index: 1688752 (The Pile)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1990. Min Range: -1.1990
Max Act: 1.0242. Min Act: -0.0001
Data Index: 904751 (The Pile)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1990. Min Range: -1.1990
Max Act: 0.9905. Min Act: -0.0001
Data Index: 927678 (The Pile)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1990. Min Range: -1.1990
Max Act: 1.0189. Min Act: -0.0001
Data Index: 558608 (The Pile)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1990. Min Range: -1.1990
Max Act: 1.0191. Min Act: -0.0001
Data Index: 1222265 (The Pile)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1990. Min Range: -1.1990
Max Act: 1.0185. Min Act: -0.0001
Data Index: 1622091 (The Pile)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1990. Min Range: -1.1990
Max Act: 1.0106. Min Act: -0.0001
Data Index: 720603 (The Pile)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1990. Min Range: -1.1990
Max Act: 1.0079. Min Act: -0.0001
Data Index: 314037 (The Pile)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1990. Min Range: -1.1990
Max Act: 0.9953. Min Act: -0.0001
Data Index: 195352 (The Pile)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1990. Min Range: -1.1990
Max Act: 0.9971. Min Act: -0.0001
Data Index: 1755336 (The Pile)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1990. Min Range: -1.1990
Max Act: 0.9885. Min Act: -0.0001
Data Index: 715147 (The Pile)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19