Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 3089 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.5030. Min Range: -2.5030
Max Act: 2.5030. Min Act: -0.0000
Data Index: 1995282 (The Pile)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5030. Min Range: -2.5030
Max Act: 2.2934. Min Act: -0.0000
Data Index: 1195890 (The Pile)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5030. Min Range: -2.5030
Max Act: 2.1293. Min Act: -0.0000
Data Index: 534703 (The Pile)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5030. Min Range: -2.5030
Max Act: 2.1239. Min Act: -0.0000
Data Index: 914550 (The Pile)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5030. Min Range: -2.5030
Max Act: 2.1047. Min Act: -0.0000
Data Index: 970990 (The Pile)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5030. Min Range: -2.5030
Max Act: 1.8449. Min Act: -0.0000
Data Index: 854003 (The Pile)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5030. Min Range: -2.5030
Max Act: 1.9617. Min Act: -0.0000
Data Index: 1002284 (The Pile)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5030. Min Range: -2.5030
Max Act: 1.8810. Min Act: -0.0000
Data Index: 1811912 (The Pile)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5030. Min Range: -2.5030
Max Act: 1.8501. Min Act: -0.0000
Data Index: 23499 (The Pile)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5030. Min Range: -2.5030
Max Act: 1.7249. Min Act: -0.0000
Data Index: 1441703 (The Pile)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5030. Min Range: -2.5030
Max Act: 1.7211. Min Act: -0.0000
Data Index: 241809 (The Pile)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5030. Min Range: -2.5030
Max Act: 1.7837. Min Act: -0.0000
Data Index: 465057 (The Pile)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5030. Min Range: -2.5030
Max Act: 1.6598. Min Act: -0.0000
Data Index: 1390902 (The Pile)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5030. Min Range: -2.5030
Max Act: 1.8314. Min Act: -0.0000
Data Index: 250513 (The Pile)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5030. Min Range: -2.5030
Max Act: 1.7167. Min Act: -0.0000
Data Index: 926965 (The Pile)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5030. Min Range: -2.5030
Max Act: 1.7020. Min Act: -0.0000
Data Index: 1854778 (The Pile)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5030. Min Range: -2.5030
Max Act: 1.6917. Min Act: -0.0000
Data Index: 1450947 (The Pile)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5030. Min Range: -2.5030
Max Act: 1.5783. Min Act: -0.0000
Data Index: 532652 (The Pile)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5030. Min Range: -2.5030
Max Act: 1.4867. Min Act: -0.0000
Data Index: 1826379 (The Pile)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5030. Min Range: -2.5030
Max Act: 1.7483. Min Act: -0.0000
Data Index: 1184649 (The Pile)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19