Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 218 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 0.7811. Min Range: -0.7811
Max Act: 0.7811. Min Act: -0.0003
Data Index: 530449 (The Pile)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7811. Min Range: -0.7811
Max Act: 0.7166. Min Act: -0.0003
Data Index: 1040283 (The Pile)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7811. Min Range: -0.7811
Max Act: 0.6954. Min Act: -0.0003
Data Index: 1802415 (The Pile)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7811. Min Range: -0.7811
Max Act: 0.6901. Min Act: -0.0003
Data Index: 855888 (The Pile)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7811. Min Range: -0.7811
Max Act: 0.6920. Min Act: -0.0003
Data Index: 600100 (The Pile)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7811. Min Range: -0.7811
Max Act: 0.6909. Min Act: -0.0003
Data Index: 1518323 (The Pile)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7811. Min Range: -0.7811
Max Act: 0.6772. Min Act: -0.0003
Data Index: 137398 (The Pile)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7811. Min Range: -0.7811
Max Act: 0.6350. Min Act: -0.0003
Data Index: 1160338 (The Pile)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7811. Min Range: -0.7811
Max Act: 0.6519. Min Act: -0.0003
Data Index: 652760 (The Pile)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7811. Min Range: -0.7811
Max Act: 0.6298. Min Act: -0.0003
Data Index: 1541422 (The Pile)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7811. Min Range: -0.7811
Max Act: 0.6270. Min Act: -0.0003
Data Index: 331919 (The Pile)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7811. Min Range: -0.7811
Max Act: 0.6447. Min Act: -0.0003
Data Index: 1315950 (The Pile)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7811. Min Range: -0.7811
Max Act: 0.6183. Min Act: -0.0003
Data Index: 1670275 (The Pile)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7811. Min Range: -0.7811
Max Act: 0.5978. Min Act: -0.0003
Data Index: 257971 (The Pile)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7811. Min Range: -0.7811
Max Act: 0.6540. Min Act: -0.0003
Data Index: 819496 (The Pile)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7811. Min Range: -0.7811
Max Act: 0.6298. Min Act: -0.0003
Data Index: 586462 (The Pile)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7811. Min Range: -0.7811
Max Act: 0.6239. Min Act: -0.0003
Data Index: 1608691 (The Pile)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7811. Min Range: -0.7811
Max Act: 0.6246. Min Act: -0.0003
Data Index: 676751 (The Pile)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7811. Min Range: -0.7811
Max Act: 0.6051. Min Act: -0.0003
Data Index: 17097 (The Pile)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7811. Min Range: -0.7811
Max Act: 0.6014. Min Act: -0.0003
Data Index: 36230 (The Pile)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19