Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 323 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 2.2010. Min Range: -2.2010
Max Act: 2.2010. Min Act: -0.0001
Data Index: 434189 (The Pile)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2010. Min Range: -2.2010
Max Act: 2.0934. Min Act: -0.0001
Data Index: 122262 (The Pile)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2010. Min Range: -2.2010
Max Act: 2.0085. Min Act: -0.0001
Data Index: 1296870 (The Pile)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2010. Min Range: -2.2010
Max Act: 1.9442. Min Act: -0.0001
Data Index: 1273047 (The Pile)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2010. Min Range: -2.2010
Max Act: 1.9124. Min Act: -0.0001
Data Index: 944910 (The Pile)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2010. Min Range: -2.2010
Max Act: 1.7562. Min Act: -0.0001
Data Index: 337057 (The Pile)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2010. Min Range: -2.2010
Max Act: 1.7558. Min Act: -0.0001
Data Index: 1686657 (The Pile)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2010. Min Range: -2.2010
Max Act: 1.7998. Min Act: -0.0001
Data Index: 1523008 (The Pile)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2010. Min Range: -2.2010
Max Act: 1.6021. Min Act: -0.0001
Data Index: 1756658 (The Pile)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2010. Min Range: -2.2010
Max Act: 1.6455. Min Act: -0.0001
Data Index: 1300300 (The Pile)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2010. Min Range: -2.2010
Max Act: 1.6113. Min Act: -0.0001
Data Index: 17552 (The Pile)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2010. Min Range: -2.2010
Max Act: 1.5715. Min Act: -0.0001
Data Index: 882842 (The Pile)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2010. Min Range: -2.2010
Max Act: 1.6272. Min Act: -0.0001
Data Index: 1078645 (The Pile)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2010. Min Range: -2.2010
Max Act: 1.5512. Min Act: -0.0001
Data Index: 315384 (The Pile)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2010. Min Range: -2.2010
Max Act: 1.5874. Min Act: -0.0001
Data Index: 770001 (The Pile)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2010. Min Range: -2.2010
Max Act: 1.5323. Min Act: -0.0001
Data Index: 179395 (The Pile)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2010. Min Range: -2.2010
Max Act: 1.5120. Min Act: -0.0001
Data Index: 1779960 (The Pile)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2010. Min Range: -2.2010
Max Act: 1.4988. Min Act: -0.0001
Data Index: 469742 (The Pile)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2010. Min Range: -2.2010
Max Act: 1.4988. Min Act: -0.0001
Data Index: 562648 (The Pile)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2010. Min Range: -2.2010
Max Act: 1.4776. Min Act: -0.0001
Data Index: 1486120 (The Pile)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19