Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1960 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0452. Min Range: -6.0452
Max Act: 6.0140. Min Act: -0.1700
Data Index: 927364 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0452. Min Range: -6.0452
Max Act: 6.0452. Min Act: -0.1700
Data Index: 4396136 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0452. Min Range: -6.0452
Max Act: 5.9202. Min Act: -0.1700
Data Index: 7513303 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0452. Min Range: -6.0452
Max Act: 5.8577. Min Act: -0.1700
Data Index: 4239594 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0452. Min Range: -6.0452
Max Act: 5.8577. Min Act: -0.1700
Data Index: 4209029 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0452. Min Range: -6.0452
Max Act: 5.8265. Min Act: -0.1700
Data Index: 893934 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0452. Min Range: -6.0452
Max Act: 5.7952. Min Act: -0.1700
Data Index: 7362845 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0452. Min Range: -6.0452
Max Act: 5.7952. Min Act: -0.1700
Data Index: 781944 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0452. Min Range: -6.0452
Max Act: 5.7640. Min Act: -0.1700
Data Index: 2268616 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0452. Min Range: -6.0452
Max Act: 5.7327. Min Act: -0.1700
Data Index: 629818 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0452. Min Range: -6.0452
Max Act: 5.7327. Min Act: -0.1700
Data Index: 7018598 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0452. Min Range: -6.0452
Max Act: 5.7015. Min Act: -0.1700
Data Index: 3409958 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0452. Min Range: -6.0452
Max Act: 5.7015. Min Act: -0.1700
Data Index: 7099400 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0452. Min Range: -6.0452
Max Act: 5.7015. Min Act: -0.1700
Data Index: 2740687 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0452. Min Range: -6.0452
Max Act: 5.6702. Min Act: -0.1700
Data Index: 4502763 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0452. Min Range: -6.0452
Max Act: 5.6390. Min Act: -0.1700
Data Index: 1488495 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0452. Min Range: -6.0452
Max Act: 5.6702. Min Act: -0.1700
Data Index: 4825020 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0452. Min Range: -6.0452
Max Act: 5.6390. Min Act: -0.1700
Data Index: 4057153 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0452. Min Range: -6.0452
Max Act: 5.6702. Min Act: -0.1700
Data Index: 7068986 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0452. Min Range: -6.0452
Max Act: 5.6390. Min Act: -0.1700
Data Index: 1650640 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #19