Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 735 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2648. Min Range: -7.2648
Max Act: 7.2648. Min Act: -0.1700
Data Index: 2700508 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2648. Min Range: -7.2648
Max Act: 7.1398. Min Act: -0.1700
Data Index: 4477745 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2648. Min Range: -7.2648
Max Act: 7.1085. Min Act: -0.1700
Data Index: 1246917 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2648. Min Range: -7.2648
Max Act: 7.0148. Min Act: -0.1700
Data Index: 336219 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2648. Min Range: -7.2648
Max Act: 6.9210. Min Act: -0.1700
Data Index: 2443530 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2648. Min Range: -7.2648
Max Act: 6.9210. Min Act: -0.1700
Data Index: 7472650 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2648. Min Range: -7.2648
Max Act: 6.9210. Min Act: -0.1700
Data Index: 6509953 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2648. Min Range: -7.2648
Max Act: 6.8898. Min Act: -0.1700
Data Index: 7520547 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2648. Min Range: -7.2648
Max Act: 6.8898. Min Act: -0.1700
Data Index: 7243491 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2648. Min Range: -7.2648
Max Act: 6.8898. Min Act: -0.1700
Data Index: 8531306 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2648. Min Range: -7.2648
Max Act: 6.8898. Min Act: -0.1700
Data Index: 6164874 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2648. Min Range: -7.2648
Max Act: 6.8898. Min Act: -0.1700
Data Index: 5358907 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2648. Min Range: -7.2648
Max Act: 6.8585. Min Act: -0.1700
Data Index: 5805195 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2648. Min Range: -7.2648
Max Act: 6.8273. Min Act: -0.1700
Data Index: 8371235 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2648. Min Range: -7.2648
Max Act: 6.8273. Min Act: -0.1700
Data Index: 43996 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2648. Min Range: -7.2648
Max Act: 6.8273. Min Act: -0.1700
Data Index: 4060412 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2648. Min Range: -7.2648
Max Act: 6.7960. Min Act: -0.1700
Data Index: 3481113 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2648. Min Range: -7.2648
Max Act: 6.7960. Min Act: -0.1700
Data Index: 940887 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2648. Min Range: -7.2648
Max Act: 6.7335. Min Act: -0.1700
Data Index: 5642300 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2648. Min Range: -7.2648
Max Act: 6.7335. Min Act: -0.1700
Data Index: 7515085 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19