Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 2549 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.3156. Min Range: -1.3156
Max Act: 1.2631. Min Act: -0.0001
Data Index: 1345847 (The Pile)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3156. Min Range: -1.3156
Max Act: 1.3156. Min Act: -0.0001
Data Index: 122145 (The Pile)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3156. Min Range: -1.3156
Max Act: 1.3106. Min Act: -0.0001
Data Index: 245086 (The Pile)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3156. Min Range: -1.3156
Max Act: 1.3137. Min Act: -0.0001
Data Index: 1248915 (The Pile)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3156. Min Range: -1.3156
Max Act: 1.1970. Min Act: -0.0001
Data Index: 827896 (The Pile)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3156. Min Range: -1.3156
Max Act: 1.2072. Min Act: -0.0001
Data Index: 161930 (The Pile)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3156. Min Range: -1.3156
Max Act: 1.2080. Min Act: -0.0001
Data Index: 971054 (The Pile)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3156. Min Range: -1.3156
Max Act: 1.2247. Min Act: -0.0001
Data Index: 255974 (The Pile)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3156. Min Range: -1.3156
Max Act: 1.1735. Min Act: -0.0001
Data Index: 275482 (The Pile)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3156. Min Range: -1.3156
Max Act: 1.2140. Min Act: -0.0001
Data Index: 560309 (The Pile)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3156. Min Range: -1.3156
Max Act: 1.2323. Min Act: -0.0001
Data Index: 1583146 (The Pile)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3156. Min Range: -1.3156
Max Act: 1.1807. Min Act: -0.0001
Data Index: 1051971 (The Pile)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3156. Min Range: -1.3156
Max Act: 1.2131. Min Act: -0.0001
Data Index: 1879692 (The Pile)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3156. Min Range: -1.3156
Max Act: 1.2151. Min Act: -0.0001
Data Index: 1037941 (The Pile)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3156. Min Range: -1.3156
Max Act: 1.2049. Min Act: -0.0001
Data Index: 889618 (The Pile)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3156. Min Range: -1.3156
Max Act: 1.2058. Min Act: -0.0001
Data Index: 1270043 (The Pile)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3156. Min Range: -1.3156
Max Act: 1.2594. Min Act: -0.0001
Data Index: 45559 (The Pile)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3156. Min Range: -1.3156
Max Act: 1.1944. Min Act: -0.0001
Data Index: 370046 (The Pile)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3156. Min Range: -1.3156
Max Act: 1.2567. Min Act: -0.0001
Data Index: 843630 (The Pile)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3156. Min Range: -1.3156
Max Act: 1.1664. Min Act: -0.0001
Data Index: 1678146 (The Pile)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19