Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1799 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.3370. Min Act: -0.1700
Data Index: 6636932 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.3370. Min Act: -0.1700
Data Index: 2028980 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.2120. Min Act: -0.1700
Data Index: 2713928 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.2120. Min Act: -0.1700
Data Index: 3278469 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.1808. Min Act: -0.1700
Data Index: 8220518 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.2120. Min Act: -0.1700
Data Index: 1268557 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.1495. Min Act: -0.1700
Data Index: 1252902 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.0870. Min Act: -0.1700
Data Index: 506103 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.0558. Min Act: -0.1700
Data Index: 264774 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.0558. Min Act: -0.1700
Data Index: 6039163 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.0558. Min Act: -0.1700
Data Index: 5133178 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.0245. Min Act: -0.1700
Data Index: 1336663 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.0245. Min Act: -0.1700
Data Index: 1293343 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3370. Min Range: -5.3370
Max Act: 4.9933. Min Act: -0.1700
Data Index: 3766794 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3370. Min Range: -5.3370
Max Act: 5.0245. Min Act: -0.1700
Data Index: 1402857 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3370. Min Range: -5.3370
Max Act: 4.9933. Min Act: -0.1700
Data Index: 4560312 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3370. Min Range: -5.3370
Max Act: 4.9933. Min Act: -0.1700
Data Index: 4085173 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3370. Min Range: -5.3370
Max Act: 4.9620. Min Act: -0.1700
Data Index: 5989627 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3370. Min Range: -5.3370
Max Act: 4.9620. Min Act: -0.1700
Data Index: 3280466 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3370. Min Range: -5.3370
Max Act: 4.9308. Min Act: -0.1700
Data Index: 558585 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #19