Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3110 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1561. Min Range: -4.1561
Max Act: 4.1561. Min Act: -0.1700
Data Index: 8648279 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1561. Min Range: -4.1561
Max Act: 4.1248. Min Act: -0.1700
Data Index: 6462594 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1561. Min Range: -4.1561
Max Act: 4.0310. Min Act: -0.1700
Data Index: 6081280 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1561. Min Range: -4.1561
Max Act: 3.9998. Min Act: -0.1700
Data Index: 1680266 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1561. Min Range: -4.1561
Max Act: 3.9998. Min Act: -0.1700
Data Index: 3314838 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1561. Min Range: -4.1561
Max Act: 3.9373. Min Act: -0.1700
Data Index: 7346233 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1561. Min Range: -4.1561
Max Act: 3.9060. Min Act: -0.1700
Data Index: 5711323 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1561. Min Range: -4.1561
Max Act: 3.8904. Min Act: -0.1700
Data Index: 1696068 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1561. Min Range: -4.1561
Max Act: 3.9373. Min Act: -0.1700
Data Index: 1225452 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1561. Min Range: -4.1561
Max Act: 3.9060. Min Act: -0.1700
Data Index: 2035472 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1561. Min Range: -4.1561
Max Act: 3.8904. Min Act: -0.1700
Data Index: 6081298 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1561. Min Range: -4.1561
Max Act: 3.8591. Min Act: -0.1700
Data Index: 1790868 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1561. Min Range: -4.1561
Max Act: 3.8591. Min Act: -0.1700
Data Index: 106288 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1561. Min Range: -4.1561
Max Act: 3.8435. Min Act: -0.1700
Data Index: 8103437 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1561. Min Range: -4.1561
Max Act: 3.8591. Min Act: -0.1700
Data Index: 8725930 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1561. Min Range: -4.1561
Max Act: 3.8278. Min Act: -0.1700
Data Index: 1201872 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1561. Min Range: -4.1561
Max Act: 3.8435. Min Act: -0.1700
Data Index: 8648278 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1561. Min Range: -4.1561
Max Act: 3.8435. Min Act: -0.1700
Data Index: 3408317 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1561. Min Range: -4.1561
Max Act: 3.8435. Min Act: -0.1700
Data Index: 4346912 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1561. Min Range: -4.1561
Max Act: 3.8435. Min Act: -0.1700
Data Index: 3238770 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19