Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3893 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0536. Min Range: -8.0536
Max Act: 8.0536. Min Act: -0.1700
Data Index: 7892826 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0536. Min Range: -8.0536
Max Act: 8.0536. Min Act: -0.1700
Data Index: 1005450 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.9911. Min Act: -0.1700
Data Index: 8294695 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.9286. Min Act: -0.1700
Data Index: 6292920 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.9286. Min Act: -0.1700
Data Index: 2340095 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.9286. Min Act: -0.1700
Data Index: 654329 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.9286. Min Act: -0.1700
Data Index: 376032 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.8661. Min Act: -0.1700
Data Index: 4922913 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.8661. Min Act: -0.1700
Data Index: 2985205 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.8661. Min Act: -0.1700
Data Index: 3435210 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.8036. Min Act: -0.1700
Data Index: 8243665 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.8036. Min Act: -0.1700
Data Index: 4513824 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.8036. Min Act: -0.1700
Data Index: 1568455 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.8036. Min Act: -0.1700
Data Index: 8564330 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.7411. Min Act: -0.1700
Data Index: 1827235 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.7411. Min Act: -0.1700
Data Index: 7302464 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.6786. Min Act: -0.1700
Data Index: 3043229 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.6786. Min Act: -0.1700
Data Index: 2048092 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.6786. Min Act: -0.1700
Data Index: 2849810 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0536. Min Range: -8.0536
Max Act: 7.6786. Min Act: -0.1700
Data Index: 22206 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19