Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2674 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0307. Min Range: -8.0307
Max Act: 8.0307. Min Act: -0.1700
Data Index: 5264422 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0307. Min Range: -8.0307
Max Act: 7.9057. Min Act: -0.1700
Data Index: 1428828 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0307. Min Range: -8.0307
Max Act: 7.6244. Min Act: -0.1700
Data Index: 4875057 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0307. Min Range: -8.0307
Max Act: 7.5307. Min Act: -0.1700
Data Index: 472644 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0307. Min Range: -8.0307
Max Act: 7.4994. Min Act: -0.1700
Data Index: 938113 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0307. Min Range: -8.0307
Max Act: 7.4994. Min Act: -0.1700
Data Index: 3758257 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0307. Min Range: -8.0307
Max Act: 7.4994. Min Act: -0.1700
Data Index: 7873355 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0307. Min Range: -8.0307
Max Act: 7.4682. Min Act: -0.1700
Data Index: 6147029 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0307. Min Range: -8.0307
Max Act: 7.4682. Min Act: -0.1700
Data Index: 1713555 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0307. Min Range: -8.0307
Max Act: 7.4994. Min Act: -0.1700
Data Index: 3146279 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0307. Min Range: -8.0307
Max Act: 7.4682. Min Act: -0.1700
Data Index: 1362881 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0307. Min Range: -8.0307
Max Act: 7.4682. Min Act: -0.1700
Data Index: 2594641 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0307. Min Range: -8.0307
Max Act: 7.4057. Min Act: -0.1700
Data Index: 6782743 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0307. Min Range: -8.0307
Max Act: 7.4369. Min Act: -0.1700
Data Index: 7265523 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0307. Min Range: -8.0307
Max Act: 7.4057. Min Act: -0.1700
Data Index: 1015859 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0307. Min Range: -8.0307
Max Act: 7.4057. Min Act: -0.1700
Data Index: 3120131 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0307. Min Range: -8.0307
Max Act: 7.4057. Min Act: -0.1700
Data Index: 6772129 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0307. Min Range: -8.0307
Max Act: 7.3744. Min Act: -0.1700
Data Index: 6313562 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0307. Min Range: -8.0307
Max Act: 7.3744. Min Act: -0.1700
Data Index: 8760877 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0307. Min Range: -8.0307
Max Act: 7.3744. Min Act: -0.1700
Data Index: 8612338 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19