Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 2394 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.4741. Min Range: -0.4741
Max Act: 0.4707. Min Act: -0.0001
Data Index: 328702 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4741. Min Range: -0.4741
Max Act: 0.4707. Min Act: -0.0001
Data Index: 1044526 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4741. Min Range: -0.4741
Max Act: 0.4606. Min Act: -0.0001
Data Index: 987682 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4741. Min Range: -0.4741
Max Act: 0.4643. Min Act: -0.0001
Data Index: 21228 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4741. Min Range: -0.4741
Max Act: 0.4741. Min Act: -0.0001
Data Index: 1935115 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4741. Min Range: -0.4741
Max Act: 0.4303. Min Act: -0.0001
Data Index: 1180784 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4741. Min Range: -0.4741
Max Act: 0.4183. Min Act: -0.0001
Data Index: 690754 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4741. Min Range: -0.4741
Max Act: 0.4166. Min Act: -0.0001
Data Index: 1261482 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4741. Min Range: -0.4741
Max Act: 0.4138. Min Act: -0.0001
Data Index: 848604 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4741. Min Range: -0.4741
Max Act: 0.3869. Min Act: -0.0001
Data Index: 1450945 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4741. Min Range: -0.4741
Max Act: 0.4365. Min Act: -0.0001
Data Index: 1838573 (The Pile)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4741. Min Range: -0.4741
Max Act: 0.3957. Min Act: -0.0001
Data Index: 1685278 (The Pile)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4741. Min Range: -0.4741
Max Act: 0.3813. Min Act: -0.0001
Data Index: 598758 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4741. Min Range: -0.4741
Max Act: 0.3752. Min Act: -0.0001
Data Index: 561090 (The Pile)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4741. Min Range: -0.4741
Max Act: 0.3700. Min Act: -0.0001
Data Index: 1341341 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4741. Min Range: -0.4741
Max Act: 0.4210. Min Act: -0.0001
Data Index: 776882 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4741. Min Range: -0.4741
Max Act: 0.3753. Min Act: -0.0001
Data Index: 1592084 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4741. Min Range: -0.4741
Max Act: 0.4029. Min Act: -0.0001
Data Index: 1009135 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4741. Min Range: -0.4741
Max Act: 0.3945. Min Act: -0.0001
Data Index: 1873393 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4741. Min Range: -0.4741
Max Act: 0.3696. Min Act: -0.0001
Data Index: 1812146 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #19