Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2290 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.6043. Min Range: -1.6043
Max Act: 1.6043. Min Act: -0.0001
Data Index: 1879015 (The Pile)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6043. Min Range: -1.6043
Max Act: 1.3596. Min Act: -0.0001
Data Index: 561124 (The Pile)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6043. Min Range: -1.6043
Max Act: 1.2198. Min Act: -0.0001
Data Index: 1684803 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6043. Min Range: -1.6043
Max Act: 1.2894. Min Act: -0.0001
Data Index: 483403 (The Pile)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6043. Min Range: -1.6043
Max Act: 1.2039. Min Act: -0.0001
Data Index: 1275157 (The Pile)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6043. Min Range: -1.6043
Max Act: 1.1340. Min Act: -0.0001
Data Index: 667587 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6043. Min Range: -1.6043
Max Act: 1.0650. Min Act: -0.0001
Data Index: 1060541 (The Pile)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6043. Min Range: -1.6043
Max Act: 1.0902. Min Act: -0.0001
Data Index: 970618 (The Pile)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6043. Min Range: -1.6043
Max Act: 1.0202. Min Act: -0.0001
Data Index: 139127 (The Pile)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6043. Min Range: -1.6043
Max Act: 1.0971. Min Act: -0.0001
Data Index: 700446 (The Pile)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6043. Min Range: -1.6043
Max Act: 1.1367. Min Act: -0.0001
Data Index: 1280007 (The Pile)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6043. Min Range: -1.6043
Max Act: 1.0210. Min Act: -0.0001
Data Index: 584761 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6043. Min Range: -1.6043
Max Act: 1.0917. Min Act: -0.0001
Data Index: 1518571 (The Pile)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6043. Min Range: -1.6043
Max Act: 1.0073. Min Act: -0.0001
Data Index: 773873 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6043. Min Range: -1.6043
Max Act: 1.0102. Min Act: -0.0001
Data Index: 294048 (The Pile)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6043. Min Range: -1.6043
Max Act: 1.2198. Min Act: -0.0001
Data Index: 1892693 (The Pile)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6043. Min Range: -1.6043
Max Act: 0.9857. Min Act: -0.0001
Data Index: 989390 (The Pile)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6043. Min Range: -1.6043
Max Act: 1.0745. Min Act: -0.0001
Data Index: 452196 (The Pile)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6043. Min Range: -1.6043
Max Act: 0.9959. Min Act: -0.0001
Data Index: 563494 (The Pile)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6043. Min Range: -1.6043
Max Act: 0.9226. Min Act: -0.0001
Data Index: 357879 (The Pile)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19