Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1975 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1438. Min Range: -6.1438
Max Act: 6.1438. Min Act: -0.1700
Data Index: 5157254 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1438. Min Range: -6.1438
Max Act: 6.1438. Min Act: -0.1700
Data Index: 1658344 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1438. Min Range: -6.1438
Max Act: 6.0500. Min Act: -0.1700
Data Index: 4118669 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.8313. Min Act: -0.1700
Data Index: 8618243 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.8313. Min Act: -0.1700
Data Index: 8119304 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.7688. Min Act: -0.1700
Data Index: 5446913 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.7688. Min Act: -0.1700
Data Index: 4959293 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.7688. Min Act: -0.1700
Data Index: 6813453 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.6750. Min Act: -0.1700
Data Index: 8580875 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.7063. Min Act: -0.1700
Data Index: 4083760 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.6750. Min Act: -0.1700
Data Index: 7879076 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.6750. Min Act: -0.1700
Data Index: 7970451 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.6125. Min Act: -0.1700
Data Index: 6925564 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.6438. Min Act: -0.1700
Data Index: 2576053 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.6125. Min Act: -0.1700
Data Index: 522659 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.6125. Min Act: -0.1700
Data Index: 2254709 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.6125. Min Act: -0.1700
Data Index: 5163365 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.6125. Min Act: -0.1700
Data Index: 2751449 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.5813. Min Act: -0.1700
Data Index: 7980909 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1438. Min Range: -6.1438
Max Act: 5.5813. Min Act: -0.1700
Data Index: 5008324 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19