Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 755 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7562. Min Range: -4.7562
Max Act: 4.7250. Min Act: -0.1700
Data Index: 5720364 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7562. Min Range: -4.7562
Max Act: 4.7562. Min Act: -0.1700
Data Index: 1694515 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7562. Min Range: -4.7562
Max Act: 4.6937. Min Act: -0.1700
Data Index: 623492 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7562. Min Range: -4.7562
Max Act: 4.6937. Min Act: -0.1700
Data Index: 6238366 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7562. Min Range: -4.7562
Max Act: 4.6625. Min Act: -0.1700
Data Index: 5161992 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7562. Min Range: -4.7562
Max Act: 4.6312. Min Act: -0.1700
Data Index: 8125118 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7562. Min Range: -4.7562
Max Act: 4.6312. Min Act: -0.1700
Data Index: 58744 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7562. Min Range: -4.7562
Max Act: 4.6000. Min Act: -0.1700
Data Index: 2955765 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7562. Min Range: -4.7562
Max Act: 4.5687. Min Act: -0.1700
Data Index: 2789962 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7562. Min Range: -4.7562
Max Act: 4.6000. Min Act: -0.1700
Data Index: 8601551 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7562. Min Range: -4.7562
Max Act: 4.5687. Min Act: -0.1700
Data Index: 5527443 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7562. Min Range: -4.7562
Max Act: 4.5687. Min Act: -0.1700
Data Index: 5370964 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7562. Min Range: -4.7562
Max Act: 4.5375. Min Act: -0.1700
Data Index: 907693 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7562. Min Range: -4.7562
Max Act: 4.5062. Min Act: -0.1700
Data Index: 6133826 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7562. Min Range: -4.7562
Max Act: 4.5062. Min Act: -0.1700
Data Index: 3998928 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7562. Min Range: -4.7562
Max Act: 4.5062. Min Act: -0.1700
Data Index: 6971444 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7562. Min Range: -4.7562
Max Act: 4.5375. Min Act: -0.1700
Data Index: 7352234 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7562. Min Range: -4.7562
Max Act: 4.5062. Min Act: -0.1700
Data Index: 4314355 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7562. Min Range: -4.7562
Max Act: 4.5062. Min Act: -0.1700
Data Index: 1781727 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7562. Min Range: -4.7562
Max Act: 4.5062. Min Act: -0.1700
Data Index: 4525748 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19