Model: None
Dataset: The Pile
Neuron 2070 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')
Text #0
Max Range: 44.8874. Min Range: -44.8874
Max Act: 44.8874. Min Act: -0.1700
Data Index: 6174808 (The Pile)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 44.8874. Min Range: -44.8874
Max Act: 40.8874. Min Act: -0.0000
Data Index: 26918 (The Pile)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 44.8874. Min Range: -44.8874
Max Act: 39.3874. Min Act: -0.1503
Data Index: 7976655 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 44.8874. Min Range: -44.8874
Max Act: 39.1374. Min Act: -0.0058
Data Index: 2298978 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 44.8874. Min Range: -44.8874
Max Act: 38.8874. Min Act: -0.1248
Data Index: 10679081 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 44.8874. Min Range: -44.8874
Max Act: 38.8874. Min Act: -0.0001
Data Index: 2078537 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 44.8874. Min Range: -44.8874
Max Act: 38.6374. Min Act: -0.0754
Data Index: 9815487 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 44.8874. Min Range: -44.8874
Max Act: 38.1374. Min Act: -0.0293
Data Index: 3352512 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 44.8874. Min Range: -44.8874
Max Act: 38.1374. Min Act: -0.1436
Data Index: 10554882 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 44.8874. Min Range: -44.8874
Max Act: 38.1374. Min Act: -0.1227
Data Index: 778834 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 44.8874. Min Range: -44.8874
Max Act: 37.8874. Min Act: -0.0810
Data Index: 5284035 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 44.8874. Min Range: -44.8874
Max Act: 37.8874. Min Act: -0.0001
Data Index: 6346882 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 44.8874. Min Range: -44.8874
Max Act: 37.8874. Min Act: -0.0254
Data Index: 7924313 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 44.8874. Min Range: -44.8874
Max Act: 37.8874. Min Act: -0.1219
Data Index: 1280789 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 44.8874. Min Range: -44.8874
Max Act: 37.6374. Min Act: -0.1668
Data Index: 2245920 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 44.8874. Min Range: -44.8874
Max Act: 37.6374. Min Act: -0.1128
Data Index: 7778232 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 44.8874. Min Range: -44.8874
Max Act: 37.6374. Min Act: -0.0024
Data Index: 6903687 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 44.8874. Min Range: -44.8874
Max Act: 37.6374. Min Act: -0.0008
Data Index: 6689255 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 44.8874. Min Range: -44.8874
Max Act: 37.6374. Min Act: -0.1519
Data Index: 2793297 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 44.8874. Min Range: -44.8874
Max Act: 37.6374. Min Act: -0.1669
Data Index: 2664699 (The Pile)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #19