Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4688 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0859. Min Range: -6.0859
Max Act: 6.0859. Min Act: -0.1700
Data Index: 6920327 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0859. Min Range: -6.0859
Max Act: 6.0859. Min Act: -0.1700
Data Index: 4096120 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0859. Min Range: -6.0859
Max Act: 5.8672. Min Act: -0.1700
Data Index: 3243340 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0859. Min Range: -6.0859
Max Act: 5.7109. Min Act: -0.1700
Data Index: 327794 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0859. Min Range: -6.0859
Max Act: 5.7422. Min Act: -0.1700
Data Index: 6750623 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0859. Min Range: -6.0859
Max Act: 5.7422. Min Act: -0.1700
Data Index: 8475430 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0859. Min Range: -6.0859
Max Act: 5.7422. Min Act: -0.1700
Data Index: 4849245 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0859. Min Range: -6.0859
Max Act: 5.6797. Min Act: -0.1700
Data Index: 832096 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0859. Min Range: -6.0859
Max Act: 5.6797. Min Act: -0.1700
Data Index: 1834775 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0859. Min Range: -6.0859
Max Act: 5.6797. Min Act: -0.1700
Data Index: 3297065 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0859. Min Range: -6.0859
Max Act: 5.6484. Min Act: -0.1700
Data Index: 8448685 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0859. Min Range: -6.0859
Max Act: 5.6484. Min Act: -0.1700
Data Index: 327796 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0859. Min Range: -6.0859
Max Act: 5.6172. Min Act: -0.1700
Data Index: 5358655 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0859. Min Range: -6.0859
Max Act: 5.6172. Min Act: -0.1700
Data Index: 3849219 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0859. Min Range: -6.0859
Max Act: 5.5859. Min Act: -0.1700
Data Index: 7327793 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0859. Min Range: -6.0859
Max Act: 5.5859. Min Act: -0.1700
Data Index: 2881814 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0859. Min Range: -6.0859
Max Act: 5.5547. Min Act: -0.1700
Data Index: 8068679 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0859. Min Range: -6.0859
Max Act: 5.5547. Min Act: -0.1700
Data Index: 2461647 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0859. Min Range: -6.0859
Max Act: 5.5234. Min Act: -0.1700
Data Index: 2833603 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0859. Min Range: -6.0859
Max Act: 5.4922. Min Act: -0.1700
Data Index: 4849252 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19