Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2799 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2814. Min Range: -5.2814
Max Act: 5.2814. Min Act: -0.1700
Data Index: 3096077 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2814. Min Range: -5.2814
Max Act: 5.2814. Min Act: -0.1700
Data Index: 8748334 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2814. Min Range: -5.2814
Max Act: 5.1876. Min Act: -0.1700
Data Index: 502419 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2814. Min Range: -5.2814
Max Act: 5.1876. Min Act: -0.1700
Data Index: 7041301 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2814. Min Range: -5.2814
Max Act: 5.1876. Min Act: -0.1700
Data Index: 7572397 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2814. Min Range: -5.2814
Max Act: 5.1876. Min Act: -0.1700
Data Index: 2483751 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2814. Min Range: -5.2814
Max Act: 5.1564. Min Act: -0.1700
Data Index: 7054670 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2814. Min Range: -5.2814
Max Act: 5.0939. Min Act: -0.1700
Data Index: 2935854 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2814. Min Range: -5.2814
Max Act: 5.0626. Min Act: -0.1700
Data Index: 7301214 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2814. Min Range: -5.2814
Max Act: 5.0626. Min Act: -0.1700
Data Index: 6772454 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2814. Min Range: -5.2814
Max Act: 5.0314. Min Act: -0.1700
Data Index: 980994 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2814. Min Range: -5.2814
Max Act: 5.0626. Min Act: -0.1700
Data Index: 3826852 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2814. Min Range: -5.2814
Max Act: 5.0314. Min Act: -0.1700
Data Index: 7762320 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2814. Min Range: -5.2814
Max Act: 5.0939. Min Act: -0.1700
Data Index: 2680347 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2814. Min Range: -5.2814
Max Act: 5.0314. Min Act: -0.1700
Data Index: 6180062 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2814. Min Range: -5.2814
Max Act: 5.0314. Min Act: -0.1700
Data Index: 4327745 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2814. Min Range: -5.2814
Max Act: 5.0314. Min Act: -0.1700
Data Index: 1243915 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2814. Min Range: -5.2814
Max Act: 5.0314. Min Act: -0.1700
Data Index: 4022293 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2814. Min Range: -5.2814
Max Act: 5.0001. Min Act: -0.1700
Data Index: 4669 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2814. Min Range: -5.2814
Max Act: 5.0001. Min Act: -0.1700
Data Index: 1511161 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19