Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3230 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1659. Min Range: -4.1659
Max Act: 4.1659. Min Act: -0.1700
Data Index: 6573660 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1659. Min Range: -4.1659
Max Act: 4.1347. Min Act: -0.1700
Data Index: 24043 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1659. Min Range: -4.1659
Max Act: 4.0722. Min Act: -0.1700
Data Index: 7929064 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1659. Min Range: -4.1659
Max Act: 4.1034. Min Act: -0.1700
Data Index: 4125517 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1659. Min Range: -4.1659
Max Act: 4.0722. Min Act: -0.1700
Data Index: 2928216 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1659. Min Range: -4.1659
Max Act: 4.0722. Min Act: -0.1700
Data Index: 4329495 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1659. Min Range: -4.1659
Max Act: 4.0097. Min Act: -0.1700
Data Index: 1173440 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1659. Min Range: -4.1659
Max Act: 4.0097. Min Act: -0.1700
Data Index: 7370028 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1659. Min Range: -4.1659
Max Act: 4.0097. Min Act: -0.1700
Data Index: 3994554 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1659. Min Range: -4.1659
Max Act: 3.9471. Min Act: -0.1700
Data Index: 2490095 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1659. Min Range: -4.1659
Max Act: 3.9471. Min Act: -0.1700
Data Index: 6796200 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1659. Min Range: -4.1659
Max Act: 3.9159. Min Act: -0.1700
Data Index: 6747718 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1659. Min Range: -4.1659
Max Act: 3.8533. Min Act: -0.1700
Data Index: 3992378 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1659. Min Range: -4.1659
Max Act: 3.8846. Min Act: -0.1700
Data Index: 2122141 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1659. Min Range: -4.1659
Max Act: 3.8846. Min Act: -0.1700
Data Index: 4837790 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1659. Min Range: -4.1659
Max Act: 3.8846. Min Act: -0.1700
Data Index: 5617306 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1659. Min Range: -4.1659
Max Act: 3.8846. Min Act: -0.1700
Data Index: 3273881 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1659. Min Range: -4.1659
Max Act: 3.8846. Min Act: -0.1700
Data Index: 3685920 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1659. Min Range: -4.1659
Max Act: 3.8533. Min Act: -0.1700
Data Index: 5048225 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1659. Min Range: -4.1659
Max Act: 3.8533. Min Act: -0.1700
Data Index: 687511 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #19