Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 636 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.8217. Min Range: -1.8217
Max Act: 1.8217. Min Act: -0.0001
Data Index: 1697232 (The Pile)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8217. Min Range: -1.8217
Max Act: 1.6323. Min Act: -0.0001
Data Index: 454636 (The Pile)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8217. Min Range: -1.8217
Max Act: 1.6931. Min Act: -0.0001
Data Index: 617306 (The Pile)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8217. Min Range: -1.8217
Max Act: 1.4825. Min Act: -0.0001
Data Index: 1117356 (The Pile)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8217. Min Range: -1.8217
Max Act: 1.6856. Min Act: -0.0001
Data Index: 1056053 (The Pile)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8217. Min Range: -1.8217
Max Act: 1.5384. Min Act: -0.0001
Data Index: 1048182 (The Pile)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8217. Min Range: -1.8217
Max Act: 1.6041. Min Act: -0.0001
Data Index: 1970163 (The Pile)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8217. Min Range: -1.8217
Max Act: 1.4582. Min Act: -0.0001
Data Index: 600276 (The Pile)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8217. Min Range: -1.8217
Max Act: 1.5282. Min Act: -0.0001
Data Index: 639248 (The Pile)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8217. Min Range: -1.8217
Max Act: 1.4514. Min Act: -0.0001
Data Index: 491821 (The Pile)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8217. Min Range: -1.8217
Max Act: 1.5345. Min Act: -0.0001
Data Index: 666672 (The Pile)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8217. Min Range: -1.8217
Max Act: 1.5361. Min Act: -0.0001
Data Index: 1909968 (The Pile)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8217. Min Range: -1.8217
Max Act: 1.3316. Min Act: -0.0001
Data Index: 554149 (The Pile)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8217. Min Range: -1.8217
Max Act: 1.4301. Min Act: -0.0001
Data Index: 1106068 (The Pile)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8217. Min Range: -1.8217
Max Act: 1.3850. Min Act: -0.0001
Data Index: 1312515 (The Pile)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8217. Min Range: -1.8217
Max Act: 1.4759. Min Act: -0.0001
Data Index: 982275 (The Pile)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8217. Min Range: -1.8217
Max Act: 1.5106. Min Act: -0.0001
Data Index: 780484 (The Pile)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8217. Min Range: -1.8217
Max Act: 1.2743. Min Act: -0.0001
Data Index: 591729 (The Pile)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8217. Min Range: -1.8217
Max Act: 1.3825. Min Act: -0.0001
Data Index: 948983 (The Pile)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8217. Min Range: -1.8217
Max Act: 1.4113. Min Act: -0.0001
Data Index: 618517 (The Pile)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19