Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2221 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.5429. Min Range: -0.5429
Max Act: 0.5429. Min Act: 0.0000
Data Index: 947935 (The Pile)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5429. Min Range: -0.5429
Max Act: 0.5180. Min Act: 0.0000
Data Index: 1082048 (The Pile)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5429. Min Range: -0.5429
Max Act: 0.5231. Min Act: 0.0005
Data Index: 1115074 (The Pile)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5429. Min Range: -0.5429
Max Act: 0.5007. Min Act: 0.0000
Data Index: 1732520 (The Pile)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5429. Min Range: -0.5429
Max Act: 0.4947. Min Act: 0.0007
Data Index: 213256 (The Pile)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5429. Min Range: -0.5429
Max Act: 0.5428. Min Act: 0.0006
Data Index: 530789 (The Pile)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5429. Min Range: -0.5429
Max Act: 0.4492. Min Act: 0.0005
Data Index: 1815844 (The Pile)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5429. Min Range: -0.5429
Max Act: 0.4620. Min Act: 0.0003
Data Index: 56603 (The Pile)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5429. Min Range: -0.5429
Max Act: 0.4483. Min Act: 0.0008
Data Index: 771555 (The Pile)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5429. Min Range: -0.5429
Max Act: 0.4095. Min Act: 0.0005
Data Index: 340109 (The Pile)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5429. Min Range: -0.5429
Max Act: 0.4089. Min Act: 0.0002
Data Index: 182475 (The Pile)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5429. Min Range: -0.5429
Max Act: 0.3896. Min Act: 0.0007
Data Index: 1647384 (The Pile)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5429. Min Range: -0.5429
Max Act: 0.3934. Min Act: 0.0005
Data Index: 1109015 (The Pile)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5429. Min Range: -0.5429
Max Act: 0.3856. Min Act: 0.0008
Data Index: 1325682 (The Pile)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5429. Min Range: -0.5429
Max Act: 0.3797. Min Act: 0.0001
Data Index: 1100763 (The Pile)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5429. Min Range: -0.5429
Max Act: 0.3767. Min Act: 0.0011
Data Index: 85324 (The Pile)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5429. Min Range: -0.5429
Max Act: 0.3277. Min Act: 0.0001
Data Index: 43698 (The Pile)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5429. Min Range: -0.5429
Max Act: 0.3927. Min Act: 0.0009
Data Index: 1178882 (The Pile)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5429. Min Range: -0.5429
Max Act: 0.4060. Min Act: 0.0005
Data Index: 542432 (The Pile)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5429. Min Range: -0.5429
Max Act: 0.4067. Min Act: 0.0005
Data Index: 1973649 (The Pile)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #19