Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 1026 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 0.1941. Min Range: -0.1941
Max Act: 0.1941. Min Act: -0.0001
Data Index: 1637441 (The Pile)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1941. Min Range: -0.1941
Max Act: 0.1842. Min Act: -0.0001
Data Index: 1379128 (The Pile)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1941. Min Range: -0.1941
Max Act: 0.1620. Min Act: -0.0001
Data Index: 1763722 (The Pile)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1941. Min Range: -0.1941
Max Act: 0.1487. Min Act: -0.0001
Data Index: 305150 (The Pile)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1941. Min Range: -0.1941
Max Act: 0.1479. Min Act: -0.0001
Data Index: 1536904 (The Pile)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1941. Min Range: -0.1941
Max Act: 0.1284. Min Act: -0.0001
Data Index: 635904 (The Pile)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1941. Min Range: -0.1941
Max Act: 0.1307. Min Act: -0.0001
Data Index: 1725560 (The Pile)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1941. Min Range: -0.1941
Max Act: 0.1151. Min Act: -0.0001
Data Index: 1290671 (The Pile)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1941. Min Range: -0.1941
Max Act: 0.1183. Min Act: -0.0001
Data Index: 559277 (The Pile)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1941. Min Range: -0.1941
Max Act: 0.1095. Min Act: -0.0001
Data Index: 25634 (The Pile)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1941. Min Range: -0.1941
Max Act: 0.1084. Min Act: -0.0001
Data Index: 285636 (The Pile)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1941. Min Range: -0.1941
Max Act: 0.1113. Min Act: -0.0001
Data Index: 1515991 (The Pile)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1941. Min Range: -0.1941
Max Act: 0.1024. Min Act: -0.0001
Data Index: 237948 (The Pile)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1941. Min Range: -0.1941
Max Act: 0.1216. Min Act: -0.0001
Data Index: 131418 (The Pile)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1941. Min Range: -0.1941
Max Act: 0.1264. Min Act: -0.0001
Data Index: 618809 (The Pile)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1941. Min Range: -0.1941
Max Act: 0.0979. Min Act: -0.0001
Data Index: 1968792 (The Pile)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1941. Min Range: -0.1941
Max Act: 0.1025. Min Act: -0.0001
Data Index: 1859886 (The Pile)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1941. Min Range: -0.1941
Max Act: 0.0991. Min Act: -0.0001
Data Index: 1897407 (The Pile)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1941. Min Range: -0.1941
Max Act: 0.0928. Min Act: -0.0001
Data Index: 321054 (The Pile)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1941. Min Range: -0.1941
Max Act: 0.0998. Min Act: -0.0001
Data Index: 479182 (The Pile)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19