Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 411 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8510. Min Range: -4.8510
Max Act: 4.8510. Min Act: -0.1700
Data Index: 1246423 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8510. Min Range: -4.8510
Max Act: 4.7885. Min Act: -0.1700
Data Index: 694684 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8510. Min Range: -4.8510
Max Act: 4.7885. Min Act: -0.1700
Data Index: 1676724 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8510. Min Range: -4.8510
Max Act: 4.7572. Min Act: -0.1700
Data Index: 1696793 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8510. Min Range: -4.8510
Max Act: 4.7572. Min Act: -0.1700
Data Index: 2722524 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8510. Min Range: -4.8510
Max Act: 4.6947. Min Act: -0.1700
Data Index: 6686804 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8510. Min Range: -4.8510
Max Act: 4.7572. Min Act: -0.1700
Data Index: 6822581 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8510. Min Range: -4.8510
Max Act: 4.6947. Min Act: -0.1700
Data Index: 4030949 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8510. Min Range: -4.8510
Max Act: 4.6947. Min Act: -0.1700
Data Index: 8033249 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8510. Min Range: -4.8510
Max Act: 4.6947. Min Act: -0.1700
Data Index: 3093375 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8510. Min Range: -4.8510
Max Act: 4.6322. Min Act: -0.1700
Data Index: 1113815 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8510. Min Range: -4.8510
Max Act: 4.6635. Min Act: -0.1700
Data Index: 6927418 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8510. Min Range: -4.8510
Max Act: 4.6635. Min Act: -0.1700
Data Index: 6121421 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8510. Min Range: -4.8510
Max Act: 4.6322. Min Act: -0.1700
Data Index: 7288192 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8510. Min Range: -4.8510
Max Act: 4.6322. Min Act: -0.1700
Data Index: 2189675 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8510. Min Range: -4.8510
Max Act: 4.6322. Min Act: -0.1700
Data Index: 3960081 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8510. Min Range: -4.8510
Max Act: 4.6010. Min Act: -0.1700
Data Index: 1389928 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8510. Min Range: -4.8510
Max Act: 4.6010. Min Act: -0.1700
Data Index: 2376303 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8510. Min Range: -4.8510
Max Act: 4.6010. Min Act: -0.1700
Data Index: 554907 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8510. Min Range: -4.8510
Max Act: 4.6010. Min Act: -0.1700
Data Index: 5008159 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #19