Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2138 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.7328. Min Range: -7.7328
Max Act: 7.7328. Min Act: -0.1700
Data Index: 1036501 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7328. Min Range: -7.7328
Max Act: 7.6391. Min Act: -0.1700
Data Index: 428706 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7328. Min Range: -7.7328
Max Act: 7.4203. Min Act: -0.1700
Data Index: 7044902 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7328. Min Range: -7.7328
Max Act: 7.3266. Min Act: -0.1700
Data Index: 3310107 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7328. Min Range: -7.7328
Max Act: 7.2641. Min Act: -0.1700
Data Index: 4913780 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7328. Min Range: -7.7328
Max Act: 7.2328. Min Act: -0.1700
Data Index: 1570826 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7328. Min Range: -7.7328
Max Act: 7.1391. Min Act: -0.1700
Data Index: 2738235 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7328. Min Range: -7.7328
Max Act: 7.0766. Min Act: -0.1700
Data Index: 7717157 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7328. Min Range: -7.7328
Max Act: 7.0141. Min Act: -0.1700
Data Index: 7001621 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7328. Min Range: -7.7328
Max Act: 7.0141. Min Act: -0.1700
Data Index: 8013762 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7328. Min Range: -7.7328
Max Act: 7.1078. Min Act: -0.1700
Data Index: 660370 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7328. Min Range: -7.7328
Max Act: 7.0453. Min Act: -0.1700
Data Index: 4546242 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7328. Min Range: -7.7328
Max Act: 7.0141. Min Act: -0.1700
Data Index: 5250115 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7328. Min Range: -7.7328
Max Act: 7.0141. Min Act: -0.1700
Data Index: 2827854 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7328. Min Range: -7.7328
Max Act: 6.9828. Min Act: -0.1700
Data Index: 2738234 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7328. Min Range: -7.7328
Max Act: 6.9516. Min Act: -0.1700
Data Index: 7230077 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7328. Min Range: -7.7328
Max Act: 6.9516. Min Act: -0.1700
Data Index: 1779805 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7328. Min Range: -7.7328
Max Act: 6.9516. Min Act: -0.1700
Data Index: 4097827 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7328. Min Range: -7.7328
Max Act: 6.9828. Min Act: -0.1700
Data Index: 3904445 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7328. Min Range: -7.7328
Max Act: 6.9516. Min Act: -0.1700
Data Index: 5429075 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #19