Model: None
Dataset: The Pile
Neuron 1584 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')
Text #0
Max Range: 3.1880. Min Range: -3.1880
Max Act: 3.1880. Min Act: -0.1700
Data Index: 10621098 (The Pile)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1880. Min Range: -3.1880
Max Act: 3.1565. Min Act: -0.1700
Data Index: 2173084 (The Pile)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1880. Min Range: -3.1880
Max Act: 3.0935. Min Act: -0.1700
Data Index: 5983956 (The Pile)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1880. Min Range: -3.1880
Max Act: 3.0777. Min Act: -0.1700
Data Index: 6369959 (The Pile)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1880. Min Range: -3.1880
Max Act: 3.0777. Min Act: -0.1700
Data Index: 10395689 (The Pile)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1880. Min Range: -3.1880
Max Act: 2.9354. Min Act: -0.1700
Data Index: 10271925 (The Pile)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1880. Min Range: -3.1880
Max Act: 2.9196. Min Act: -0.1700
Data Index: 9337013 (The Pile)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1880. Min Range: -3.1880
Max Act: 2.9196. Min Act: -0.1700
Data Index: 8848170 (The Pile)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1880. Min Range: -3.1880
Max Act: 2.9196. Min Act: -0.1700
Data Index: 3112160 (The Pile)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1880. Min Range: -3.1880
Max Act: 2.9037. Min Act: -0.1700
Data Index: 581679 (The Pile)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1880. Min Range: -3.1880
Max Act: 2.9037. Min Act: -0.1700
Data Index: 5298285 (The Pile)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1880. Min Range: -3.1880
Max Act: 2.9037. Min Act: -0.1700
Data Index: 4881582 (The Pile)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1880. Min Range: -3.1880
Max Act: 2.9037. Min Act: -0.1700
Data Index: 5410 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1880. Min Range: -3.1880
Max Act: 2.9037. Min Act: -0.1700
Data Index: 281022 (The Pile)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1880. Min Range: -3.1880
Max Act: 2.9037. Min Act: -0.1700
Data Index: 2257897 (The Pile)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1880. Min Range: -3.1880
Max Act: 2.8879. Min Act: -0.1700
Data Index: 5137374 (The Pile)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1880. Min Range: -3.1880
Max Act: 2.8879. Min Act: -0.1700
Data Index: 4002258 (The Pile)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1880. Min Range: -3.1880
Max Act: 2.8879. Min Act: -0.1700
Data Index: 666956 (The Pile)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1880. Min Range: -3.1880
Max Act: 2.8879. Min Act: -0.1700
Data Index: 3942325 (The Pile)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1880. Min Range: -3.1880
Max Act: 2.8879. Min Act: -0.1700
Data Index: 8874031 (The Pile)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19