Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2965 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5939. Min Range: -6.5939
Max Act: 6.1251. Min Act: -0.1700
Data Index: 2092746 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5939. Min Range: -6.5939
Max Act: 6.5939. Min Act: -0.1700
Data Index: 2783817 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5939. Min Range: -6.5939
Max Act: 4.9376. Min Act: -0.1700
Data Index: 6222692 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5939. Min Range: -6.5939
Max Act: 5.7814. Min Act: -0.1700
Data Index: 4464480 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5939. Min Range: -6.5939
Max Act: 5.6251. Min Act: -0.1700
Data Index: 2467233 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5939. Min Range: -6.5939
Max Act: 5.1564. Min Act: -0.1700
Data Index: 5819334 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5939. Min Range: -6.5939
Max Act: 5.4689. Min Act: -0.1700
Data Index: 4101786 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5939. Min Range: -6.5939
Max Act: 4.6251. Min Act: -0.1699
Data Index: 4134191 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5939. Min Range: -6.5939
Max Act: 5.1251. Min Act: -0.1700
Data Index: 6622166 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5939. Min Range: -6.5939
Max Act: 5.3439. Min Act: -0.1700
Data Index: 2310421 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5939. Min Range: -6.5939
Max Act: 5.3126. Min Act: -0.1700
Data Index: 5233363 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5939. Min Range: -6.5939
Max Act: 5.3126. Min Act: -0.1700
Data Index: 6867629 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5939. Min Range: -6.5939
Max Act: 5.4064. Min Act: -0.1700
Data Index: 4879939 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5939. Min Range: -6.5939
Max Act: 5.1876. Min Act: -0.1700
Data Index: 3544983 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5939. Min Range: -6.5939
Max Act: 5.2189. Min Act: -0.1700
Data Index: 480062 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5939. Min Range: -6.5939
Max Act: 4.6876. Min Act: -0.1700
Data Index: 4566578 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5939. Min Range: -6.5939
Max Act: 5.1876. Min Act: -0.1700
Data Index: 4292161 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5939. Min Range: -6.5939
Max Act: 5.1564. Min Act: -0.1700
Data Index: 708727 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5939. Min Range: -6.5939
Max Act: 5.1876. Min Act: -0.1700
Data Index: 5978246 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5939. Min Range: -6.5939
Max Act: 5.1564. Min Act: -0.1700
Data Index: 3785478 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19