Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 429 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1811. Min Range: -5.1811
Max Act: 5.1811. Min Act: -0.1700
Data Index: 3427284 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1811. Min Range: -5.1811
Max Act: 5.0561. Min Act: -0.1700
Data Index: 1925159 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1811. Min Range: -5.1811
Max Act: 5.0561. Min Act: -0.1700
Data Index: 5290923 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1811. Min Range: -5.1811
Max Act: 5.0249. Min Act: -0.1700
Data Index: 425623 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1811. Min Range: -5.1811
Max Act: 5.0249. Min Act: -0.1700
Data Index: 3612885 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1811. Min Range: -5.1811
Max Act: 4.9624. Min Act: -0.1700
Data Index: 4872071 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1811. Min Range: -5.1811
Max Act: 4.8999. Min Act: -0.1700
Data Index: 8629495 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1811. Min Range: -5.1811
Max Act: 4.9311. Min Act: -0.1700
Data Index: 1054212 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1811. Min Range: -5.1811
Max Act: 4.9311. Min Act: -0.1700
Data Index: 692873 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1811. Min Range: -5.1811
Max Act: 4.9311. Min Act: -0.1700
Data Index: 1989220 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1811. Min Range: -5.1811
Max Act: 4.9311. Min Act: -0.1700
Data Index: 940408 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1811. Min Range: -5.1811
Max Act: 4.9311. Min Act: -0.1700
Data Index: 2830874 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1811. Min Range: -5.1811
Max Act: 4.8999. Min Act: -0.1700
Data Index: 1363484 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1811. Min Range: -5.1811
Max Act: 4.9311. Min Act: -0.1700
Data Index: 8420803 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1811. Min Range: -5.1811
Max Act: 4.8999. Min Act: -0.1700
Data Index: 6413434 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1811. Min Range: -5.1811
Max Act: 4.8999. Min Act: -0.1700
Data Index: 6572957 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1811. Min Range: -5.1811
Max Act: 4.8999. Min Act: -0.1700
Data Index: 8643354 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1811. Min Range: -5.1811
Max Act: 4.8999. Min Act: -0.1700
Data Index: 8169135 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1811. Min Range: -5.1811
Max Act: 4.8686. Min Act: -0.1700
Data Index: 4479295 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1811. Min Range: -5.1811
Max Act: 4.8686. Min Act: -0.1700
Data Index: 7583605 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19