Model: None
Dataset: The Pile
Neuron 1702 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')
Text #0
Max Range: 2.9618. Min Range: -2.9618
Max Act: 2.9618. Min Act: -0.1700
Data Index: 1989468 (The Pile)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9618. Min Range: -2.9618
Max Act: 2.8666. Min Act: -0.1700
Data Index: 238901 (The Pile)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9618. Min Range: -2.9618
Max Act: 2.8349. Min Act: -0.1700
Data Index: 3193705 (The Pile)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9618. Min Range: -2.9618
Max Act: 2.8189. Min Act: -0.1700
Data Index: 1275803 (The Pile)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9618. Min Range: -2.9618
Max Act: 2.8189. Min Act: -0.1700
Data Index: 8321687 (The Pile)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9618. Min Range: -2.9618
Max Act: 2.8030. Min Act: -0.1700
Data Index: 4925813 (The Pile)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9618. Min Range: -2.9618
Max Act: 2.7871. Min Act: -0.1700
Data Index: 7320959 (The Pile)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9618. Min Range: -2.9618
Max Act: 2.7871. Min Act: -0.1700
Data Index: 8377891 (The Pile)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9618. Min Range: -2.9618
Max Act: 2.7871. Min Act: -0.1700
Data Index: 3018562 (The Pile)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9618. Min Range: -2.9618
Max Act: 2.7712. Min Act: -0.1700
Data Index: 2751377 (The Pile)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9618. Min Range: -2.9618
Max Act: 2.7552. Min Act: -0.1700
Data Index: 6770712 (The Pile)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9618. Min Range: -2.9618
Max Act: 2.7552. Min Act: -0.1700
Data Index: 1276327 (The Pile)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9618. Min Range: -2.9618
Max Act: 2.7392. Min Act: -0.1700
Data Index: 1627052 (The Pile)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9618. Min Range: -2.9618
Max Act: 2.7392. Min Act: -0.1700
Data Index: 4922742 (The Pile)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9618. Min Range: -2.9618
Max Act: 2.7392. Min Act: -0.1700
Data Index: 5420612 (The Pile)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9618. Min Range: -2.9618
Max Act: 2.7392. Min Act: -0.1700
Data Index: 4693732 (The Pile)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9618. Min Range: -2.9618
Max Act: 2.7392. Min Act: -0.1700
Data Index: 5206745 (The Pile)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9618. Min Range: -2.9618
Max Act: 2.7392. Min Act: -0.1700
Data Index: 7951848 (The Pile)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9618. Min Range: -2.9618
Max Act: 2.7233. Min Act: -0.1700
Data Index: 2685355 (The Pile)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9618. Min Range: -2.9618
Max Act: 2.7233. Min Act: -0.1700
Data Index: 6957118 (The Pile)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #19