Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2096 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7876. Min Range: -4.7876
Max Act: 4.7876. Min Act: -0.1700
Data Index: 2252265 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7876. Min Range: -4.7876
Max Act: 4.7876. Min Act: -0.1700
Data Index: 5724215 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7876. Min Range: -4.7876
Max Act: 4.6939. Min Act: -0.1700
Data Index: 6904813 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7876. Min Range: -4.7876
Max Act: 4.6314. Min Act: -0.1700
Data Index: 8232276 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7876. Min Range: -4.7876
Max Act: 4.5689. Min Act: -0.1700
Data Index: 5257970 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7876. Min Range: -4.7876
Max Act: 4.5064. Min Act: -0.1700
Data Index: 803085 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7876. Min Range: -4.7876
Max Act: 4.5064. Min Act: -0.1700
Data Index: 8729736 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7876. Min Range: -4.7876
Max Act: 4.4751. Min Act: -0.1700
Data Index: 6408299 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7876. Min Range: -4.7876
Max Act: 4.4751. Min Act: -0.1700
Data Index: 161088 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7876. Min Range: -4.7876
Max Act: 4.4751. Min Act: -0.1700
Data Index: 3780807 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7876. Min Range: -4.7876
Max Act: 4.4439. Min Act: -0.1700
Data Index: 5817747 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7876. Min Range: -4.7876
Max Act: 4.4126. Min Act: -0.1700
Data Index: 6408297 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7876. Min Range: -4.7876
Max Act: 4.4751. Min Act: -0.1700
Data Index: 8270626 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7876. Min Range: -4.7876
Max Act: 4.4439. Min Act: -0.1700
Data Index: 1595039 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7876. Min Range: -4.7876
Max Act: 4.4439. Min Act: -0.1700
Data Index: 4494276 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7876. Min Range: -4.7876
Max Act: 4.4126. Min Act: -0.1700
Data Index: 7223600 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7876. Min Range: -4.7876
Max Act: 4.3814. Min Act: -0.1700
Data Index: 8089698 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7876. Min Range: -4.7876
Max Act: 4.4126. Min Act: -0.1700
Data Index: 5635634 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7876. Min Range: -4.7876
Max Act: 4.3814. Min Act: -0.1700
Data Index: 6146000 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7876. Min Range: -4.7876
Max Act: 4.3814. Min Act: -0.1700
Data Index: 2201466 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19