Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 2455 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 0.8175. Min Range: -0.8175
Max Act: 0.8175. Min Act: -0.0002
Data Index: 991267 (The Pile)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8175. Min Range: -0.8175
Max Act: 0.7937. Min Act: -0.0002
Data Index: 1335636 (The Pile)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8175. Min Range: -0.8175
Max Act: 0.7990. Min Act: -0.0002
Data Index: 1110934 (The Pile)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8175. Min Range: -0.8175
Max Act: 0.7493. Min Act: -0.0002
Data Index: 1422342 (The Pile)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8175. Min Range: -0.8175
Max Act: 0.7531. Min Act: -0.0002
Data Index: 1901621 (The Pile)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8175. Min Range: -0.8175
Max Act: 0.7635. Min Act: -0.0002
Data Index: 1049652 (The Pile)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8175. Min Range: -0.8175
Max Act: 0.6634. Min Act: -0.0002
Data Index: 478669 (The Pile)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8175. Min Range: -0.8175
Max Act: 0.7279. Min Act: -0.0002
Data Index: 178208 (The Pile)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8175. Min Range: -0.8175
Max Act: 0.7181. Min Act: -0.0002
Data Index: 442017 (The Pile)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8175. Min Range: -0.8175
Max Act: 0.7030. Min Act: -0.0002
Data Index: 1955114 (The Pile)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8175. Min Range: -0.8175
Max Act: 0.6962. Min Act: -0.0002
Data Index: 999437 (The Pile)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8175. Min Range: -0.8175
Max Act: 0.7373. Min Act: -0.0002
Data Index: 832137 (The Pile)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8175. Min Range: -0.8175
Max Act: 0.7112. Min Act: -0.0002
Data Index: 115378 (The Pile)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8175. Min Range: -0.8175
Max Act: 0.7070. Min Act: -0.0002
Data Index: 921729 (The Pile)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8175. Min Range: -0.8175
Max Act: 0.6989. Min Act: -0.0002
Data Index: 322493 (The Pile)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8175. Min Range: -0.8175
Max Act: 0.7071. Min Act: -0.0002
Data Index: 1501502 (The Pile)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8175. Min Range: -0.8175
Max Act: 0.6979. Min Act: -0.0002
Data Index: 723969 (The Pile)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8175. Min Range: -0.8175
Max Act: 0.7098. Min Act: -0.0002
Data Index: 619104 (The Pile)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8175. Min Range: -0.8175
Max Act: 0.6603. Min Act: -0.0002
Data Index: 534161 (The Pile)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8175. Min Range: -0.8175
Max Act: 0.6835. Min Act: -0.0002
Data Index: 720856 (The Pile)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19