Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3227 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5452. Min Range: -6.5452
Max Act: 6.5452. Min Act: -0.1700
Data Index: 1100009 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5452. Min Range: -6.5452
Max Act: 6.2640. Min Act: -0.1700
Data Index: 6071717 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5452. Min Range: -6.5452
Max Act: 6.1390. Min Act: -0.1700
Data Index: 4736689 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5452. Min Range: -6.5452
Max Act: 5.9827. Min Act: -0.1700
Data Index: 6367105 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5452. Min Range: -6.5452
Max Act: 5.9515. Min Act: -0.1700
Data Index: 4965899 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5452. Min Range: -6.5452
Max Act: 5.9515. Min Act: -0.1700
Data Index: 4322892 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5452. Min Range: -6.5452
Max Act: 5.9202. Min Act: -0.1700
Data Index: 2055369 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5452. Min Range: -6.5452
Max Act: 5.9202. Min Act: -0.1700
Data Index: 1279224 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5452. Min Range: -6.5452
Max Act: 5.9202. Min Act: -0.1700
Data Index: 7213495 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5452. Min Range: -6.5452
Max Act: 5.9515. Min Act: -0.1700
Data Index: 1664924 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5452. Min Range: -6.5452
Max Act: 5.8890. Min Act: -0.1700
Data Index: 1742406 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5452. Min Range: -6.5452
Max Act: 5.8890. Min Act: -0.1700
Data Index: 4329174 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5452. Min Range: -6.5452
Max Act: 5.8890. Min Act: -0.1700
Data Index: 241710 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5452. Min Range: -6.5452
Max Act: 5.8577. Min Act: -0.1700
Data Index: 3167384 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5452. Min Range: -6.5452
Max Act: 5.8577. Min Act: -0.1700
Data Index: 6761286 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5452. Min Range: -6.5452
Max Act: 5.8577. Min Act: -0.1700
Data Index: 4751251 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5452. Min Range: -6.5452
Max Act: 5.8577. Min Act: -0.1700
Data Index: 2062140 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5452. Min Range: -6.5452
Max Act: 5.8265. Min Act: -0.1700
Data Index: 5891955 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5452. Min Range: -6.5452
Max Act: 5.7952. Min Act: -0.1700
Data Index: 2569013 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5452. Min Range: -6.5452
Max Act: 5.7952. Min Act: -0.1700
Data Index: 2294644 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #19