Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3092 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5526. Min Range: -7.5526
Max Act: 7.5526. Min Act: -0.1700
Data Index: 1151648 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5526. Min Range: -7.5526
Max Act: 7.4276. Min Act: -0.1700
Data Index: 8344445 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5526. Min Range: -7.5526
Max Act: 7.3338. Min Act: -0.1700
Data Index: 2451009 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5526. Min Range: -7.5526
Max Act: 7.3026. Min Act: -0.1700
Data Index: 997299 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5526. Min Range: -7.5526
Max Act: 7.2401. Min Act: -0.1700
Data Index: 5105625 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5526. Min Range: -7.5526
Max Act: 7.2088. Min Act: -0.1700
Data Index: 3961580 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5526. Min Range: -7.5526
Max Act: 7.2088. Min Act: -0.1700
Data Index: 7881032 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5526. Min Range: -7.5526
Max Act: 7.2088. Min Act: -0.1700
Data Index: 1967241 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5526. Min Range: -7.5526
Max Act: 7.2088. Min Act: -0.1700
Data Index: 4924833 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5526. Min Range: -7.5526
Max Act: 7.2088. Min Act: -0.1700
Data Index: 4065980 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5526. Min Range: -7.5526
Max Act: 7.1776. Min Act: -0.1700
Data Index: 6762614 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5526. Min Range: -7.5526
Max Act: 7.1463. Min Act: -0.1700
Data Index: 8394673 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5526. Min Range: -7.5526
Max Act: 7.1151. Min Act: -0.1700
Data Index: 6098048 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5526. Min Range: -7.5526
Max Act: 7.1151. Min Act: -0.1700
Data Index: 2004004 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5526. Min Range: -7.5526
Max Act: 7.0213. Min Act: -0.1700
Data Index: 40694 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5526. Min Range: -7.5526
Max Act: 7.0526. Min Act: -0.1700
Data Index: 221514 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5526. Min Range: -7.5526
Max Act: 7.0213. Min Act: -0.1700
Data Index: 2632139 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5526. Min Range: -7.5526
Max Act: 6.9588. Min Act: -0.1700
Data Index: 5705214 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5526. Min Range: -7.5526
Max Act: 6.9588. Min Act: -0.1700
Data Index: 1209640 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5526. Min Range: -7.5526
Max Act: 6.9588. Min Act: -0.1700
Data Index: 4580177 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19