Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 178 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8719. Min Range: -3.8719
Max Act: 3.8719. Min Act: -0.1700
Data Index: 4398744 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8719. Min Range: -3.8719
Max Act: 3.7155. Min Act: -0.1700
Data Index: 4842656 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8719. Min Range: -3.8719
Max Act: 3.6060. Min Act: -0.1700
Data Index: 2906402 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8719. Min Range: -3.8719
Max Act: 3.5277. Min Act: -0.1700
Data Index: 533612 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8719. Min Range: -3.8719
Max Act: 3.4651. Min Act: -0.1700
Data Index: 5760837 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8719. Min Range: -3.8719
Max Act: 3.4808. Min Act: -0.1700
Data Index: 3686138 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8719. Min Range: -3.8719
Max Act: 3.4494. Min Act: -0.1700
Data Index: 3974055 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8719. Min Range: -3.8719
Max Act: 3.4338. Min Act: -0.1700
Data Index: 460689 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8719. Min Range: -3.8719
Max Act: 3.4338. Min Act: -0.1700
Data Index: 690294 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8719. Min Range: -3.8719
Max Act: 3.3867. Min Act: -0.1700
Data Index: 895066 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8719. Min Range: -3.8719
Max Act: 3.4181. Min Act: -0.1700
Data Index: 5856566 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8719. Min Range: -3.8719
Max Act: 3.4181. Min Act: -0.1700
Data Index: 3837678 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8719. Min Range: -3.8719
Max Act: 3.4181. Min Act: -0.1700
Data Index: 4823598 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8719. Min Range: -3.8719
Max Act: 3.3867. Min Act: -0.1700
Data Index: 3558682 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8719. Min Range: -3.8719
Max Act: 3.3867. Min Act: -0.1700
Data Index: 5856568 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8719. Min Range: -3.8719
Max Act: 3.4024. Min Act: -0.1700
Data Index: 8473748 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8719. Min Range: -3.8719
Max Act: 3.3554. Min Act: -0.1700
Data Index: 4107586 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8719. Min Range: -3.8719
Max Act: 3.3554. Min Act: -0.1700
Data Index: 2000988 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8719. Min Range: -3.8719
Max Act: 3.4024. Min Act: -0.1700
Data Index: 6237963 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8719. Min Range: -3.8719
Max Act: 3.3867. Min Act: -0.1700
Data Index: 4860569 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19