Model: None
Dataset: The Pile
Neuron 1990 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.0894. Min Act: -0.1700
Data Index: 9060982 (The Pile)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.1519. Min Act: -0.1700
Data Index: 10457883 (The Pile)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.0269. Min Act: -0.1700
Data Index: 10615261 (The Pile)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.2144. Min Act: -0.1700
Data Index: 3501145 (The Pile)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.7769. Min Act: -0.1700
Data Index: 9272626 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9332. Min Act: -0.1700
Data Index: 9691675 (The Pile)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8394. Min Act: -0.1700
Data Index: 5788431 (The Pile)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.0582. Min Act: -0.1700
Data Index: 7959719 (The Pile)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.1832. Min Act: -0.1700
Data Index: 704265 (The Pile)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.5894. Min Act: -0.1700
Data Index: 5188189 (The Pile)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.0582. Min Act: -0.1700
Data Index: 10166152 (The Pile)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9019. Min Act: -0.1700
Data Index: 5694609 (The Pile)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.0269. Min Act: -0.1700
Data Index: 10063772 (The Pile)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9957. Min Act: -0.1700
Data Index: 392246 (The Pile)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9019. Min Act: -0.1700
Data Index: 3087043 (The Pile)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2144. Min Range: -5.2144
Max Act: 5.1519. Min Act: -0.1700
Data Index: 10743288 (The Pile)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9644. Min Act: -0.1700
Data Index: 5149953 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.7144. Min Act: -0.1700
Data Index: 5038520 (The Pile)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.8394. Min Act: -0.1700
Data Index: 2635064 (The Pile)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2144. Min Range: -5.2144
Max Act: 4.9019. Min Act: -0.1700
Data Index: 840478 (The Pile)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19