Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3546 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4643. Min Range: -4.4643
Max Act: 4.4643. Min Act: -0.1700
Data Index: 5787972 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4643. Min Range: -4.4643
Max Act: 4.4330. Min Act: -0.1700
Data Index: 2238321 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4643. Min Range: -4.4643
Max Act: 4.4330. Min Act: -0.1700
Data Index: 7914645 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4643. Min Range: -4.4643
Max Act: 4.4018. Min Act: -0.1700
Data Index: 1006129 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4643. Min Range: -4.4643
Max Act: 4.3080. Min Act: -0.1700
Data Index: 5866340 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4643. Min Range: -4.4643
Max Act: 4.2767. Min Act: -0.1700
Data Index: 6348241 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4643. Min Range: -4.4643
Max Act: 4.2767. Min Act: -0.1700
Data Index: 6305150 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4643. Min Range: -4.4643
Max Act: 4.2767. Min Act: -0.1700
Data Index: 5002744 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4643. Min Range: -4.4643
Max Act: 4.2767. Min Act: -0.1700
Data Index: 1767924 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4643. Min Range: -4.4643
Max Act: 4.2767. Min Act: -0.1700
Data Index: 4424992 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4643. Min Range: -4.4643
Max Act: 4.2455. Min Act: -0.1700
Data Index: 2628482 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4643. Min Range: -4.4643
Max Act: 4.2142. Min Act: -0.1700
Data Index: 7446621 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4643. Min Range: -4.4643
Max Act: 4.2142. Min Act: -0.1700
Data Index: 3827526 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4643. Min Range: -4.4643
Max Act: 4.2142. Min Act: -0.1700
Data Index: 1549411 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4643. Min Range: -4.4643
Max Act: 4.2455. Min Act: -0.1700
Data Index: 8472195 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4643. Min Range: -4.4643
Max Act: 4.1830. Min Act: -0.1700
Data Index: 2975898 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4643. Min Range: -4.4643
Max Act: 4.1830. Min Act: -0.1700
Data Index: 3635731 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4643. Min Range: -4.4643
Max Act: 4.1830. Min Act: -0.1700
Data Index: 724116 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4643. Min Range: -4.4643
Max Act: 4.1830. Min Act: -0.1700
Data Index: 5403449 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4643. Min Range: -4.4643
Max Act: 4.1830. Min Act: -0.1700
Data Index: 5485735 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19