Model: None
Dataset: The Pile
Neuron 1403 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.3314. Min Range: -3.3314
Max Act: 3.3314. Min Act: -0.1700
Data Index: 102813 (The Pile)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3314. Min Range: -3.3314
Max Act: 3.3314. Min Act: -0.1700
Data Index: 6726939 (The Pile)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3314. Min Range: -3.3314
Max Act: 3.3314. Min Act: -0.1700
Data Index: 9411549 (The Pile)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3314. Min Range: -3.3314
Max Act: 3.2843. Min Act: -0.1700
Data Index: 4238020 (The Pile)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3314. Min Range: -3.3314
Max Act: 3.2685. Min Act: -0.1700
Data Index: 7751893 (The Pile)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3314. Min Range: -3.3314
Max Act: 3.2528. Min Act: -0.1700
Data Index: 2068275 (The Pile)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3314. Min Range: -3.3314
Max Act: 3.2371. Min Act: -0.1700
Data Index: 3800739 (The Pile)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3314. Min Range: -3.3314
Max Act: 3.2371. Min Act: -0.1700
Data Index: 958440 (The Pile)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3314. Min Range: -3.3314
Max Act: 3.2214. Min Act: -0.1700
Data Index: 5039177 (The Pile)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3314. Min Range: -3.3314
Max Act: 3.2214. Min Act: -0.1700
Data Index: 5876801 (The Pile)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3314. Min Range: -3.3314
Max Act: 3.2214. Min Act: -0.1700
Data Index: 2586192 (The Pile)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3314. Min Range: -3.3314
Max Act: 3.2057. Min Act: -0.1700
Data Index: 6834975 (The Pile)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3314. Min Range: -3.3314
Max Act: 3.2057. Min Act: -0.1700
Data Index: 5824682 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3314. Min Range: -3.3314
Max Act: 3.2057. Min Act: -0.1700
Data Index: 6380890 (The Pile)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3314. Min Range: -3.3314
Max Act: 3.1899. Min Act: -0.1700
Data Index: 3519636 (The Pile)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3314. Min Range: -3.3314
Max Act: 3.1742. Min Act: -0.1700
Data Index: 9113270 (The Pile)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3314. Min Range: -3.3314
Max Act: 3.1742. Min Act: -0.1700
Data Index: 385181 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3314. Min Range: -3.3314
Max Act: 3.1742. Min Act: -0.1700
Data Index: 6959118 (The Pile)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3314. Min Range: -3.3314
Max Act: 3.1742. Min Act: -0.1700
Data Index: 2518161 (The Pile)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3314. Min Range: -3.3314
Max Act: 3.1742. Min Act: -0.1700
Data Index: 1966502 (The Pile)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19