Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2426 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0880. Min Range: -5.0880
Max Act: 5.0880. Min Act: -0.1700
Data Index: 4504913 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0880. Min Range: -5.0880
Max Act: 5.0880. Min Act: -0.1700
Data Index: 7871242 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0880. Min Range: -5.0880
Max Act: 5.0568. Min Act: -0.1700
Data Index: 1953423 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0880. Min Range: -5.0880
Max Act: 4.9943. Min Act: -0.1700
Data Index: 1276906 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0880. Min Range: -5.0880
Max Act: 4.9318. Min Act: -0.1700
Data Index: 1823560 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0880. Min Range: -5.0880
Max Act: 4.9318. Min Act: -0.1700
Data Index: 4950150 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0880. Min Range: -5.0880
Max Act: 4.9005. Min Act: -0.1700
Data Index: 865519 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0880. Min Range: -5.0880
Max Act: 4.9318. Min Act: -0.1700
Data Index: 229455 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0880. Min Range: -5.0880
Max Act: 4.9318. Min Act: -0.1700
Data Index: 7355354 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0880. Min Range: -5.0880
Max Act: 4.9005. Min Act: -0.1700
Data Index: 7633889 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0880. Min Range: -5.0880
Max Act: 4.9005. Min Act: -0.1700
Data Index: 7555043 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0880. Min Range: -5.0880
Max Act: 4.8693. Min Act: -0.1700
Data Index: 6337754 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0880. Min Range: -5.0880
Max Act: 4.8693. Min Act: -0.1700
Data Index: 6951011 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0880. Min Range: -5.0880
Max Act: 4.8380. Min Act: -0.1700
Data Index: 5378623 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0880. Min Range: -5.0880
Max Act: 4.8693. Min Act: -0.1700
Data Index: 5769412 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0880. Min Range: -5.0880
Max Act: 4.8380. Min Act: -0.1700
Data Index: 402620 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0880. Min Range: -5.0880
Max Act: 4.8693. Min Act: -0.1700
Data Index: 1911390 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0880. Min Range: -5.0880
Max Act: 4.8693. Min Act: -0.1700
Data Index: 829894 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0880. Min Range: -5.0880
Max Act: 4.8380. Min Act: -0.1700
Data Index: 6337753 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0880. Min Range: -5.0880
Max Act: 4.7755. Min Act: -0.1700
Data Index: 4919065 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #19