Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2924 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2618. Min Range: -4.2618
Max Act: 4.2618. Min Act: -0.1700
Data Index: 5617004 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2618. Min Range: -4.2618
Max Act: 4.2305. Min Act: -0.1700
Data Index: 1390875 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2618. Min Range: -4.2618
Max Act: 4.1680. Min Act: -0.1700
Data Index: 5799451 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2618. Min Range: -4.2618
Max Act: 4.1993. Min Act: -0.1700
Data Index: 1143412 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2618. Min Range: -4.2618
Max Act: 4.1993. Min Act: -0.1700
Data Index: 5476679 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2618. Min Range: -4.2618
Max Act: 4.1993. Min Act: -0.1700
Data Index: 6353537 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2618. Min Range: -4.2618
Max Act: 4.1368. Min Act: -0.1700
Data Index: 8348215 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2618. Min Range: -4.2618
Max Act: 4.1680. Min Act: -0.1700
Data Index: 8636200 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2618. Min Range: -4.2618
Max Act: 4.1055. Min Act: -0.1700
Data Index: 7132584 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2618. Min Range: -4.2618
Max Act: 4.1055. Min Act: -0.1700
Data Index: 462085 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2618. Min Range: -4.2618
Max Act: 4.1368. Min Act: -0.1700
Data Index: 8532202 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2618. Min Range: -4.2618
Max Act: 4.1055. Min Act: -0.1700
Data Index: 2400745 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2618. Min Range: -4.2618
Max Act: 4.1055. Min Act: -0.1700
Data Index: 4110916 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2618. Min Range: -4.2618
Max Act: 4.1055. Min Act: -0.1700
Data Index: 3461573 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2618. Min Range: -4.2618
Max Act: 4.1055. Min Act: -0.1700
Data Index: 3246503 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2618. Min Range: -4.2618
Max Act: 4.0430. Min Act: -0.1700
Data Index: 7118960 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2618. Min Range: -4.2618
Max Act: 4.0430. Min Act: -0.1700
Data Index: 1503817 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2618. Min Range: -4.2618
Max Act: 4.0430. Min Act: -0.1700
Data Index: 1031986 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2618. Min Range: -4.2618
Max Act: 4.0430. Min Act: -0.1700
Data Index: 6533657 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2618. Min Range: -4.2618
Max Act: 4.0430. Min Act: -0.1700
Data Index: 3337436 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19