Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 2462 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 1.0104. Min Range: -1.0104
Max Act: 1.0104. Min Act: -0.0002
Data Index: 1348819 (The Pile)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0104. Min Range: -1.0104
Max Act: 0.9009. Min Act: -0.0002
Data Index: 493210 (The Pile)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0104. Min Range: -1.0104
Max Act: 0.7880. Min Act: -0.0002
Data Index: 1548253 (The Pile)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0104. Min Range: -1.0104
Max Act: 0.7479. Min Act: -0.0002
Data Index: 483118 (The Pile)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0104. Min Range: -1.0104
Max Act: 0.7476. Min Act: -0.0002
Data Index: 1251861 (The Pile)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0104. Min Range: -1.0104
Max Act: 0.7400. Min Act: -0.0002
Data Index: 1825306 (The Pile)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0104. Min Range: -1.0104
Max Act: 0.7380. Min Act: -0.0002
Data Index: 198144 (The Pile)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0104. Min Range: -1.0104
Max Act: 0.7290. Min Act: -0.0002
Data Index: 366004 (The Pile)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0104. Min Range: -1.0104
Max Act: 0.6733. Min Act: -0.0002
Data Index: 751106 (The Pile)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0104. Min Range: -1.0104
Max Act: 0.6694. Min Act: -0.0002
Data Index: 1770462 (The Pile)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0104. Min Range: -1.0104
Max Act: 0.6906. Min Act: -0.0002
Data Index: 217855 (The Pile)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0104. Min Range: -1.0104
Max Act: 0.6876. Min Act: -0.0002
Data Index: 661598 (The Pile)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0104. Min Range: -1.0104
Max Act: 0.6845. Min Act: -0.0002
Data Index: 81968 (The Pile)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0104. Min Range: -1.0104
Max Act: 0.7008. Min Act: -0.0002
Data Index: 155996 (The Pile)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0104. Min Range: -1.0104
Max Act: 0.6901. Min Act: -0.0002
Data Index: 30459 (The Pile)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0104. Min Range: -1.0104
Max Act: 0.6452. Min Act: -0.0002
Data Index: 457465 (The Pile)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0104. Min Range: -1.0104
Max Act: 0.6851. Min Act: -0.0002
Data Index: 129774 (The Pile)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0104. Min Range: -1.0104
Max Act: 0.6796. Min Act: -0.0002
Data Index: 1152010 (The Pile)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0104. Min Range: -1.0104
Max Act: 0.6314. Min Act: -0.0002
Data Index: 1478297 (The Pile)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0104. Min Range: -1.0104
Max Act: 0.6500. Min Act: -0.0002
Data Index: 759362 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19