Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1796 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 2.3688. Min Range: -2.3688
Max Act: 2.3688. Min Act: -0.0001
Data Index: 1885346 (The Pile)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3688. Min Range: -2.3688
Max Act: 1.9002. Min Act: -0.0001
Data Index: 1681103 (The Pile)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3688. Min Range: -2.3688
Max Act: 1.8839. Min Act: -0.0001
Data Index: 39031 (The Pile)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3688. Min Range: -2.3688
Max Act: 1.8657. Min Act: -0.0001
Data Index: 1677912 (The Pile)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3688. Min Range: -2.3688
Max Act: 1.9716. Min Act: -0.0001
Data Index: 465757 (The Pile)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3688. Min Range: -2.3688
Max Act: 1.9353. Min Act: -0.0001
Data Index: 117111 (The Pile)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3688. Min Range: -2.3688
Max Act: 1.8967. Min Act: -0.0001
Data Index: 1065174 (The Pile)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3688. Min Range: -2.3688
Max Act: 1.8672. Min Act: -0.0001
Data Index: 1628116 (The Pile)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3688. Min Range: -2.3688
Max Act: 1.8810. Min Act: -0.0001
Data Index: 1373681 (The Pile)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3688. Min Range: -2.3688
Max Act: 1.7561. Min Act: -0.0001
Data Index: 1705703 (The Pile)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3688. Min Range: -2.3688
Max Act: 1.8536. Min Act: -0.0001
Data Index: 224027 (The Pile)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3688. Min Range: -2.3688
Max Act: 1.7155. Min Act: -0.0001
Data Index: 765489 (The Pile)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3688. Min Range: -2.3688
Max Act: 1.7405. Min Act: -0.0001
Data Index: 97419 (The Pile)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3688. Min Range: -2.3688
Max Act: 1.7144. Min Act: -0.0001
Data Index: 661087 (The Pile)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3688. Min Range: -2.3688
Max Act: 1.7927. Min Act: -0.0001
Data Index: 171787 (The Pile)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3688. Min Range: -2.3688
Max Act: 1.7133. Min Act: -0.0001
Data Index: 412189 (The Pile)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3688. Min Range: -2.3688
Max Act: 1.6985. Min Act: -0.0001
Data Index: 1988871 (The Pile)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3688. Min Range: -2.3688
Max Act: 1.6691. Min Act: -0.0001
Data Index: 845002 (The Pile)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3688. Min Range: -2.3688
Max Act: 1.8273. Min Act: -0.0001
Data Index: 542835 (The Pile)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3688. Min Range: -2.3688
Max Act: 1.7307. Min Act: -0.0001
Data Index: 384050 (The Pile)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19