Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1801 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.6208. Min Range: -1.6208
Max Act: 1.6208. Min Act: -0.0000
Data Index: 980484 (The Pile)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6208. Min Range: -1.6208
Max Act: 1.1375. Min Act: -0.0000
Data Index: 1552658 (The Pile)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6208. Min Range: -1.6208
Max Act: 1.0382. Min Act: -0.0000
Data Index: 1609967 (The Pile)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6208. Min Range: -1.6208
Max Act: 0.9658. Min Act: -0.0000
Data Index: 1759044 (The Pile)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6208. Min Range: -1.6208
Max Act: 1.0029. Min Act: -0.0000
Data Index: 1025333 (The Pile)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6208. Min Range: -1.6208
Max Act: 0.9922. Min Act: -0.0000
Data Index: 1169912 (The Pile)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6208. Min Range: -1.6208
Max Act: 0.9299. Min Act: 0.0001
Data Index: 1739408 (The Pile)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6208. Min Range: -1.6208
Max Act: 0.9255. Min Act: 0.0001
Data Index: 255862 (The Pile)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6208. Min Range: -1.6208
Max Act: 0.9146. Min Act: -0.0000
Data Index: 1748373 (The Pile)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6208. Min Range: -1.6208
Max Act: 0.9127. Min Act: 0.0001
Data Index: 137238 (The Pile)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6208. Min Range: -1.6208
Max Act: 0.8418. Min Act: -0.0000
Data Index: 936107 (The Pile)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6208. Min Range: -1.6208
Max Act: 0.8916. Min Act: -0.0000
Data Index: 483832 (The Pile)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6208. Min Range: -1.6208
Max Act: 0.8572. Min Act: -0.0000
Data Index: 1213660 (The Pile)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6208. Min Range: -1.6208
Max Act: 0.9043. Min Act: -0.0000
Data Index: 349477 (The Pile)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6208. Min Range: -1.6208
Max Act: 0.8383. Min Act: 0.0001
Data Index: 472049 (The Pile)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6208. Min Range: -1.6208
Max Act: 0.8280. Min Act: 0.0002
Data Index: 405733 (The Pile)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6208. Min Range: -1.6208
Max Act: 0.8292. Min Act: -0.0000
Data Index: 1134716 (The Pile)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6208. Min Range: -1.6208
Max Act: 0.8092. Min Act: -0.0000
Data Index: 1490401 (The Pile)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6208. Min Range: -1.6208
Max Act: 0.7994. Min Act: -0.0000
Data Index: 1957532 (The Pile)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6208. Min Range: -1.6208
Max Act: 0.8037. Min Act: -0.0000
Data Index: 811987 (The Pile)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19