Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2877 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3552. Min Range: -2.3552
Max Act: 2.3552. Min Act: -0.1700
Data Index: 3253873 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3552. Min Range: -2.3552
Max Act: 2.2895. Min Act: -0.1700
Data Index: 8369995 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3552. Min Range: -2.3552
Max Act: 2.2234. Min Act: -0.1700
Data Index: 5420647 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3552. Min Range: -2.3552
Max Act: 2.2068. Min Act: -0.1700
Data Index: 1943348 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3552. Min Range: -2.3552
Max Act: 2.2068. Min Act: -0.1700
Data Index: 8491590 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3552. Min Range: -2.3552
Max Act: 2.1902. Min Act: -0.1700
Data Index: 3982899 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3552. Min Range: -2.3552
Max Act: 2.1902. Min Act: -0.1700
Data Index: 6966632 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3552. Min Range: -2.3552
Max Act: 2.1902. Min Act: -0.1700
Data Index: 1096552 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3552. Min Range: -2.3552
Max Act: 2.1902. Min Act: -0.1700
Data Index: 8264349 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3552. Min Range: -2.3552
Max Act: 2.1736. Min Act: -0.1700
Data Index: 1015456 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3552. Min Range: -2.3552
Max Act: 2.1736. Min Act: -0.1700
Data Index: 6166090 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3552. Min Range: -2.3552
Max Act: 2.1570. Min Act: -0.1700
Data Index: 1847582 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3552. Min Range: -2.3552
Max Act: 2.1570. Min Act: -0.1700
Data Index: 297444 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3552. Min Range: -2.3552
Max Act: 2.1570. Min Act: -0.1700
Data Index: 5132932 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3552. Min Range: -2.3552
Max Act: 2.1570. Min Act: -0.1700
Data Index: 882681 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3552. Min Range: -2.3552
Max Act: 2.1403. Min Act: -0.1700
Data Index: 120818 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3552. Min Range: -2.3552
Max Act: 2.1403. Min Act: -0.1700
Data Index: 135291 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3552. Min Range: -2.3552
Max Act: 2.1403. Min Act: -0.1700
Data Index: 4775431 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3552. Min Range: -2.3552
Max Act: 2.1403. Min Act: -0.1700
Data Index: 7966604 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3552. Min Range: -2.3552
Max Act: 2.1403. Min Act: -0.1700
Data Index: 233091 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #19