Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1160 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.9631. Min Range: -0.9631
Max Act: 0.8996. Min Act: -0.0001
Data Index: 445555 (The Pile)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9631. Min Range: -0.9631
Max Act: 0.9631. Min Act: -0.0001
Data Index: 1077799 (The Pile)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9631. Min Range: -0.9631
Max Act: 0.8113. Min Act: -0.0001
Data Index: 1225915 (The Pile)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9631. Min Range: -0.9631
Max Act: 0.8565. Min Act: -0.0001
Data Index: 1368186 (The Pile)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9631. Min Range: -0.9631
Max Act: 0.7774. Min Act: -0.0001
Data Index: 1999315 (The Pile)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9631. Min Range: -0.9631
Max Act: 0.8243. Min Act: -0.0001
Data Index: 330996 (The Pile)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9631. Min Range: -0.9631
Max Act: 0.7076. Min Act: -0.0001
Data Index: 375815 (The Pile)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9631. Min Range: -0.9631
Max Act: 0.7432. Min Act: -0.0001
Data Index: 1668327 (The Pile)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9631. Min Range: -0.9631
Max Act: 0.6804. Min Act: -0.0001
Data Index: 1181479 (The Pile)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9631. Min Range: -0.9631
Max Act: 0.7062. Min Act: -0.0001
Data Index: 564894 (The Pile)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9631. Min Range: -0.9631
Max Act: 0.7124. Min Act: -0.0001
Data Index: 1076811 (The Pile)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9631. Min Range: -0.9631
Max Act: 0.7741. Min Act: -0.0001
Data Index: 1635152 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9631. Min Range: -0.9631
Max Act: 0.6669. Min Act: -0.0001
Data Index: 1747118 (The Pile)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9631. Min Range: -0.9631
Max Act: 0.6616. Min Act: -0.0001
Data Index: 1128667 (The Pile)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9631. Min Range: -0.9631
Max Act: 0.6671. Min Act: -0.0001
Data Index: 895402 (The Pile)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9631. Min Range: -0.9631
Max Act: 0.6714. Min Act: -0.0001
Data Index: 512289 (The Pile)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9631. Min Range: -0.9631
Max Act: 0.6467. Min Act: -0.0001
Data Index: 1057439 (The Pile)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9631. Min Range: -0.9631
Max Act: 0.6787. Min Act: -0.0001
Data Index: 275903 (The Pile)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9631. Min Range: -0.9631
Max Act: 0.6827. Min Act: -0.0001
Data Index: 658746 (The Pile)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9631. Min Range: -0.9631
Max Act: 0.6591. Min Act: -0.0001
Data Index: 1451508 (The Pile)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19