Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4026 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5876. Min Range: -2.5876
Max Act: 2.5876. Min Act: -0.1700
Data Index: 998447 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5876. Min Range: -2.5876
Max Act: 2.4744. Min Act: -0.1700
Data Index: 6862781 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5876. Min Range: -2.5876
Max Act: 2.4257. Min Act: -0.1675
Data Index: 5840513 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5876. Min Range: -2.5876
Max Act: 2.3931. Min Act: -0.1700
Data Index: 5840514 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5876. Min Range: -2.5876
Max Act: 2.3767. Min Act: -0.1700
Data Index: 998446 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5876. Min Range: -2.5876
Max Act: 2.3111. Min Act: -0.1700
Data Index: 3829210 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5876. Min Range: -2.5876
Max Act: 2.2782. Min Act: -0.1700
Data Index: 2100473 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5876. Min Range: -2.5876
Max Act: 2.2452. Min Act: -0.1700
Data Index: 3501374 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5876. Min Range: -2.5876
Max Act: 2.2452. Min Act: -0.1700
Data Index: 8461767 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5876. Min Range: -2.5876
Max Act: 2.2287. Min Act: -0.1700
Data Index: 5399103 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5876. Min Range: -2.5876
Max Act: 2.2287. Min Act: -0.1700
Data Index: 2536705 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5876. Min Range: -2.5876
Max Act: 2.2121. Min Act: -0.1700
Data Index: 2552660 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5876. Min Range: -2.5876
Max Act: 2.1955. Min Act: -0.1700
Data Index: 645568 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5876. Min Range: -2.5876
Max Act: 2.1955. Min Act: -0.1700
Data Index: 4313210 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5876. Min Range: -2.5876
Max Act: 2.1955. Min Act: -0.1700
Data Index: 5646384 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5876. Min Range: -2.5876
Max Act: 2.1623. Min Act: -0.1700
Data Index: 2552675 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5876. Min Range: -2.5876
Max Act: 2.1456. Min Act: -0.1700
Data Index: 371107 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5876. Min Range: -2.5876
Max Act: 2.1623. Min Act: -0.1700
Data Index: 3542545 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5876. Min Range: -2.5876
Max Act: 2.1789. Min Act: -0.1700
Data Index: 634275 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5876. Min Range: -2.5876
Max Act: 2.1623. Min Act: -0.1700
Data Index: 1279517 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19