Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 958 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.2810. Min Range: -1.2810
Max Act: 1.2810. Min Act: -0.0001
Data Index: 195792 (The Pile)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2810. Min Range: -1.2810
Max Act: 1.2513. Min Act: -0.0001
Data Index: 1830705 (The Pile)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2810. Min Range: -1.2810
Max Act: 1.1752. Min Act: -0.0001
Data Index: 1962525 (The Pile)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2810. Min Range: -1.2810
Max Act: 1.2687. Min Act: -0.0001
Data Index: 1206890 (The Pile)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2810. Min Range: -1.2810
Max Act: 1.1679. Min Act: -0.0001
Data Index: 355494 (The Pile)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2810. Min Range: -1.2810
Max Act: 1.1577. Min Act: -0.0001
Data Index: 1180285 (The Pile)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2810. Min Range: -1.2810
Max Act: 1.1081. Min Act: -0.0001
Data Index: 637076 (The Pile)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2810. Min Range: -1.2810
Max Act: 1.1751. Min Act: -0.0001
Data Index: 1407683 (The Pile)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2810. Min Range: -1.2810
Max Act: 1.0882. Min Act: -0.0001
Data Index: 1082135 (The Pile)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2810. Min Range: -1.2810
Max Act: 1.1116. Min Act: -0.0001
Data Index: 24881 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2810. Min Range: -1.2810
Max Act: 1.0660. Min Act: -0.0001
Data Index: 1954357 (The Pile)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2810. Min Range: -1.2810
Max Act: 1.0870. Min Act: -0.0001
Data Index: 1996835 (The Pile)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2810. Min Range: -1.2810
Max Act: 1.0514. Min Act: -0.0001
Data Index: 782469 (The Pile)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2810. Min Range: -1.2810
Max Act: 1.1018. Min Act: -0.0001
Data Index: 602050 (The Pile)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2810. Min Range: -1.2810
Max Act: 1.0781. Min Act: -0.0001
Data Index: 540749 (The Pile)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2810. Min Range: -1.2810
Max Act: 1.0576. Min Act: -0.0001
Data Index: 253122 (The Pile)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2810. Min Range: -1.2810
Max Act: 1.0823. Min Act: -0.0001
Data Index: 1642958 (The Pile)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2810. Min Range: -1.2810
Max Act: 1.0098. Min Act: -0.0001
Data Index: 1367354 (The Pile)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2810. Min Range: -1.2810
Max Act: 1.0691. Min Act: -0.0001
Data Index: 326096 (The Pile)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2810. Min Range: -1.2810
Max Act: 1.1026. Min Act: -0.0001
Data Index: 1344624 (The Pile)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #19