Model: None
Dataset: The Pile
Neuron 1588 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.1310. Min Range: -3.1310
Max Act: 3.1310. Min Act: -0.1700
Data Index: 1018365 (The Pile)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1310. Min Range: -3.1310
Max Act: 3.0995. Min Act: -0.1700
Data Index: 8645547 (The Pile)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1310. Min Range: -3.1310
Max Act: 3.0679. Min Act: -0.1700
Data Index: 721363 (The Pile)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1310. Min Range: -3.1310
Max Act: 3.0047. Min Act: -0.1700
Data Index: 8273818 (The Pile)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1310. Min Range: -3.1310
Max Act: 3.0047. Min Act: -0.1700
Data Index: 5573597 (The Pile)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1310. Min Range: -3.1310
Max Act: 2.9889. Min Act: -0.1700
Data Index: 10277512 (The Pile)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1310. Min Range: -3.1310
Max Act: 2.9889. Min Act: -0.1700
Data Index: 8326707 (The Pile)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1310. Min Range: -3.1310
Max Act: 2.9889. Min Act: -0.1700
Data Index: 1334141 (The Pile)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1310. Min Range: -3.1310
Max Act: 2.9889. Min Act: -0.1700
Data Index: 10584415 (The Pile)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1310. Min Range: -3.1310
Max Act: 2.9731. Min Act: -0.1700
Data Index: 8912210 (The Pile)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1310. Min Range: -3.1310
Max Act: 2.9731. Min Act: -0.1700
Data Index: 7744236 (The Pile)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1310. Min Range: -3.1310
Max Act: 2.9573. Min Act: -0.1700
Data Index: 757573 (The Pile)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1310. Min Range: -3.1310
Max Act: 2.9573. Min Act: -0.1700
Data Index: 5364085 (The Pile)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1310. Min Range: -3.1310
Max Act: 2.9573. Min Act: -0.1700
Data Index: 2569925 (The Pile)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1310. Min Range: -3.1310
Max Act: 2.9573. Min Act: -0.1700
Data Index: 8729663 (The Pile)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1310. Min Range: -3.1310
Max Act: 2.9415. Min Act: -0.1700
Data Index: 4376141 (The Pile)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1310. Min Range: -3.1310
Max Act: 2.9415. Min Act: -0.1700
Data Index: 2377456 (The Pile)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1310. Min Range: -3.1310
Max Act: 2.9415. Min Act: -0.1700
Data Index: 10313309 (The Pile)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1310. Min Range: -3.1310
Max Act: 2.9256. Min Act: -0.1699
Data Index: 3749006 (The Pile)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1310. Min Range: -3.1310
Max Act: 2.9256. Min Act: -0.1700
Data Index: 1651126 (The Pile)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #19