Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1718 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.9732. Min Act: -0.1700
Data Index: 5007956 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0045. Min Range: -7.0045
Max Act: 7.0045. Min Act: -0.1700
Data Index: 8669988 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.9107. Min Act: -0.1700
Data Index: 7933095 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.8795. Min Act: -0.1700
Data Index: 334471 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.9107. Min Act: -0.1700
Data Index: 5195043 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.8482. Min Act: -0.1700
Data Index: 7686834 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.8795. Min Act: -0.1700
Data Index: 628834 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.8170. Min Act: -0.1700
Data Index: 5215390 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.8482. Min Act: -0.1700
Data Index: 2220061 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.8482. Min Act: -0.1700
Data Index: 2461767 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.8170. Min Act: -0.1700
Data Index: 7580112 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.7232. Min Act: -0.1700
Data Index: 1816800 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.7232. Min Act: -0.1700
Data Index: 3968514 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.7545. Min Act: -0.1700
Data Index: 934959 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.7232. Min Act: -0.1700
Data Index: 2501405 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.7232. Min Act: -0.1700
Data Index: 8080820 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.6920. Min Act: -0.1700
Data Index: 8597936 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.7232. Min Act: -0.1700
Data Index: 1302326 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.6920. Min Act: -0.1700
Data Index: 1212886 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0045. Min Range: -7.0045
Max Act: 6.6920. Min Act: -0.1700
Data Index: 8766301 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19