Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 574 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9807. Min Range: -6.9807
Max Act: 6.9807. Min Act: -0.1700
Data Index: 3929203 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9807. Min Range: -6.9807
Max Act: 6.9182. Min Act: -0.1700
Data Index: 5411396 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9807. Min Range: -6.9807
Max Act: 6.7932. Min Act: -0.1700
Data Index: 1958643 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9807. Min Range: -6.9807
Max Act: 6.7932. Min Act: -0.1700
Data Index: 5746515 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9807. Min Range: -6.9807
Max Act: 6.7619. Min Act: -0.1700
Data Index: 1131299 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9807. Min Range: -6.9807
Max Act: 6.6994. Min Act: -0.1700
Data Index: 601206 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9807. Min Range: -6.9807
Max Act: 6.6994. Min Act: -0.1700
Data Index: 897896 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9807. Min Range: -6.9807
Max Act: 6.6369. Min Act: -0.1700
Data Index: 7623931 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9807. Min Range: -6.9807
Max Act: 6.6057. Min Act: -0.1700
Data Index: 5426452 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9807. Min Range: -6.9807
Max Act: 6.5432. Min Act: -0.1700
Data Index: 4842750 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9807. Min Range: -6.9807
Max Act: 6.5432. Min Act: -0.1700
Data Index: 2830777 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9807. Min Range: -6.9807
Max Act: 6.5432. Min Act: -0.1700
Data Index: 7150133 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9807. Min Range: -6.9807
Max Act: 6.5119. Min Act: -0.1700
Data Index: 1663862 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9807. Min Range: -6.9807
Max Act: 6.4807. Min Act: -0.1700
Data Index: 1901843 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9807. Min Range: -6.9807
Max Act: 6.4807. Min Act: -0.1700
Data Index: 3096789 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9807. Min Range: -6.9807
Max Act: 6.4807. Min Act: -0.1700
Data Index: 2861648 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9807. Min Range: -6.9807
Max Act: 6.4182. Min Act: -0.1700
Data Index: 4938807 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9807. Min Range: -6.9807
Max Act: 6.3869. Min Act: -0.1700
Data Index: 4307454 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9807. Min Range: -6.9807
Max Act: 6.3557. Min Act: -0.1700
Data Index: 2033148 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9807. Min Range: -6.9807
Max Act: 6.3869. Min Act: -0.1700
Data Index: 1729086 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19