Model: SoLU Model: 4 Layers, 2048 Neurons per Layer
Dataset: The Pile
Neuron 1912 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')
Text #0
Max Range: 0.0460. Min Range: -0.0460
Max Act: 0.0460. Min Act: -0.0001
Data Index: 350504 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0460. Min Range: -0.0460
Max Act: 0.0460. Min Act: -0.0002
Data Index: 925987 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0460. Min Range: -0.0460
Max Act: 0.0460. Min Act: -0.0003
Data Index: 889562 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0460. Min Range: -0.0460
Max Act: 0.0460. Min Act: -0.0003
Data Index: 853094 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0460. Min Range: -0.0460
Max Act: 0.0460. Min Act: -0.0003
Data Index: 47512 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0460. Min Range: -0.0460
Max Act: 0.0460. Min Act: -0.0003
Data Index: 814990 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0460. Min Range: -0.0460
Max Act: 0.0460. Min Act: -0.0003
Data Index: 141875 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0460. Min Range: -0.0460
Max Act: 0.0460. Min Act: -0.0003
Data Index: 724788 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0460. Min Range: -0.0460
Max Act: 0.0460. Min Act: -0.0003
Data Index: 377858 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0460. Min Range: -0.0460
Max Act: 0.0460. Min Act: -0.0003
Data Index: 696805 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0460. Min Range: -0.0460
Max Act: 0.0460. Min Act: -0.0003
Data Index: 203413 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0460. Min Range: -0.0460
Max Act: 0.0460. Min Act: -0.0003
Data Index: 138992 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0460. Min Range: -0.0460
Max Act: 0.0460. Min Act: -0.0003
Data Index: 653512 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0460. Min Range: -0.0460
Max Act: 0.0460. Min Act: -0.0003
Data Index: 596514 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0460. Min Range: -0.0460
Max Act: 0.0460. Min Act: -0.0002
Data Index: 569977 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0460. Min Range: -0.0460
Max Act: 0.0460. Min Act: -0.0003
Data Index: 552088 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0460. Min Range: -0.0460
Max Act: 0.0460. Min Act: -0.0003
Data Index: 134066 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0460. Min Range: -0.0460
Max Act: 0.0460. Min Act: -0.0003
Data Index: 226964 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0460. Min Range: -0.0460
Max Act: 0.0460. Min Act: -0.0003
Data Index: 409481 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0460. Min Range: -0.0460
Max Act: 0.0460. Min Act: -0.0003
Data Index: 425299 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19