Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3470 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2639. Min Range: -5.2639
Max Act: 5.2639. Min Act: -0.1700
Data Index: 5670831 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2639. Min Range: -5.2639
Max Act: 5.2014. Min Act: -0.1700
Data Index: 5394701 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2639. Min Range: -5.2639
Max Act: 5.2014. Min Act: -0.1700
Data Index: 6395552 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2639. Min Range: -5.2639
Max Act: 5.1389. Min Act: -0.1700
Data Index: 1834885 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2639. Min Range: -5.2639
Max Act: 5.1077. Min Act: -0.1700
Data Index: 4408499 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2639. Min Range: -5.2639
Max Act: 5.1077. Min Act: -0.1700
Data Index: 7821640 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2639. Min Range: -5.2639
Max Act: 5.1077. Min Act: -0.1700
Data Index: 8194337 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2639. Min Range: -5.2639
Max Act: 5.1077. Min Act: -0.1700
Data Index: 5917391 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2639. Min Range: -5.2639
Max Act: 5.1077. Min Act: -0.1700
Data Index: 3245001 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2639. Min Range: -5.2639
Max Act: 5.1077. Min Act: -0.1700
Data Index: 5917392 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2639. Min Range: -5.2639
Max Act: 5.1077. Min Act: -0.1700
Data Index: 7462782 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2639. Min Range: -5.2639
Max Act: 5.0764. Min Act: -0.1700
Data Index: 8361833 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2639. Min Range: -5.2639
Max Act: 5.1077. Min Act: -0.1700
Data Index: 8547011 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2639. Min Range: -5.2639
Max Act: 5.1077. Min Act: -0.1700
Data Index: 8086242 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2639. Min Range: -5.2639
Max Act: 5.0764. Min Act: -0.1700
Data Index: 1617792 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2639. Min Range: -5.2639
Max Act: 5.0764. Min Act: -0.1700
Data Index: 1695349 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2639. Min Range: -5.2639
Max Act: 5.0452. Min Act: -0.1700
Data Index: 6196780 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2639. Min Range: -5.2639
Max Act: 5.0452. Min Act: -0.1700
Data Index: 8103482 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2639. Min Range: -5.2639
Max Act: 5.0452. Min Act: -0.1700
Data Index: 4381298 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2639. Min Range: -5.2639
Max Act: 5.0452. Min Act: -0.1700
Data Index: 7781250 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19