Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1229 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.3092. Min Act: -0.1700
Data Index: 2468765 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.2779. Min Act: -0.1700
Data Index: 2081488 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.2467. Min Act: -0.1700
Data Index: 2231647 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.1842. Min Act: -0.1700
Data Index: 496515 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.1529. Min Act: -0.1700
Data Index: 2121593 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.1217. Min Act: -0.1700
Data Index: 3154188 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.1217. Min Act: -0.1700
Data Index: 1725283 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.0904. Min Act: -0.1700
Data Index: 4823694 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.0592. Min Act: -0.1700
Data Index: 1040718 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.0592. Min Act: -0.1700
Data Index: 1963733 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.0592. Min Act: -0.1700
Data Index: 1963734 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.0279. Min Act: -0.1700
Data Index: 1680997 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.0904. Min Act: -0.1700
Data Index: 4234788 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.0279. Min Act: -0.1700
Data Index: 6390443 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.0279. Min Act: -0.1700
Data Index: 6131561 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.0279. Min Act: -0.1700
Data Index: 7934076 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3092. Min Range: -4.3092
Max Act: 4.0279. Min Act: -0.1700
Data Index: 4744840 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3092. Min Range: -4.3092
Max Act: 3.9966. Min Act: -0.1700
Data Index: 7927666 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3092. Min Range: -4.3092
Max Act: 3.9654. Min Act: -0.1700
Data Index: 5509623 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3092. Min Range: -4.3092
Max Act: 3.9966. Min Act: -0.1700
Data Index: 2441084 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19