Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4826 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3922. Min Range: -5.3922
Max Act: 5.3922. Min Act: -0.1700
Data Index: 5955892 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3922. Min Range: -5.3922
Max Act: 5.2672. Min Act: -0.1700
Data Index: 1403705 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3922. Min Range: -5.3922
Max Act: 5.2672. Min Act: -0.1700
Data Index: 6462536 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3922. Min Range: -5.3922
Max Act: 5.2047. Min Act: -0.1700
Data Index: 7115320 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3922. Min Range: -5.3922
Max Act: 5.1734. Min Act: -0.1700
Data Index: 8410393 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3922. Min Range: -5.3922
Max Act: 5.1109. Min Act: -0.1700
Data Index: 5497849 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3922. Min Range: -5.3922
Max Act: 5.1422. Min Act: -0.1700
Data Index: 2983348 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3922. Min Range: -5.3922
Max Act: 5.1422. Min Act: -0.1700
Data Index: 4773351 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3922. Min Range: -5.3922
Max Act: 5.1422. Min Act: -0.1700
Data Index: 2620446 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3922. Min Range: -5.3922
Max Act: 5.1109. Min Act: -0.1700
Data Index: 1713078 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3922. Min Range: -5.3922
Max Act: 5.1109. Min Act: -0.1700
Data Index: 1663903 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3922. Min Range: -5.3922
Max Act: 5.1109. Min Act: -0.1700
Data Index: 4282147 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3922. Min Range: -5.3922
Max Act: 5.0797. Min Act: -0.1700
Data Index: 8628669 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3922. Min Range: -5.3922
Max Act: 5.0484. Min Act: -0.1700
Data Index: 4355158 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3922. Min Range: -5.3922
Max Act: 5.0484. Min Act: -0.1700
Data Index: 6973766 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3922. Min Range: -5.3922
Max Act: 5.0797. Min Act: -0.1700
Data Index: 7961577 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3922. Min Range: -5.3922
Max Act: 5.0484. Min Act: -0.1700
Data Index: 3752949 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3922. Min Range: -5.3922
Max Act: 5.0484. Min Act: -0.1700
Data Index: 2358424 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3922. Min Range: -5.3922
Max Act: 5.0484. Min Act: -0.1700
Data Index: 1871646 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3922. Min Range: -5.3922
Max Act: 5.0172. Min Act: -0.1700
Data Index: 488213 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19