Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3304 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1403. Min Range: -7.1403
Max Act: 7.1403. Min Act: -0.1700
Data Index: 1853276 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1403. Min Range: -7.1403
Max Act: 7.0153. Min Act: -0.1700
Data Index: 2967590 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1403. Min Range: -7.1403
Max Act: 7.0153. Min Act: -0.1700
Data Index: 235885 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1403. Min Range: -7.1403
Max Act: 6.8903. Min Act: -0.1700
Data Index: 5098925 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1403. Min Range: -7.1403
Max Act: 6.8903. Min Act: -0.1700
Data Index: 1961948 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1403. Min Range: -7.1403
Max Act: 6.8903. Min Act: -0.1700
Data Index: 2048688 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1403. Min Range: -7.1403
Max Act: 6.8591. Min Act: -0.1700
Data Index: 4984111 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1403. Min Range: -7.1403
Max Act: 6.7966. Min Act: -0.1700
Data Index: 566386 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1403. Min Range: -7.1403
Max Act: 6.7966. Min Act: -0.1700
Data Index: 2667155 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1403. Min Range: -7.1403
Max Act: 6.7966. Min Act: -0.1700
Data Index: 3271409 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1403. Min Range: -7.1403
Max Act: 6.7653. Min Act: -0.1700
Data Index: 2060817 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1403. Min Range: -7.1403
Max Act: 6.7653. Min Act: -0.1700
Data Index: 5097732 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1403. Min Range: -7.1403
Max Act: 6.7341. Min Act: -0.1700
Data Index: 6113059 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1403. Min Range: -7.1403
Max Act: 6.6716. Min Act: -0.1700
Data Index: 5547627 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1403. Min Range: -7.1403
Max Act: 6.6403. Min Act: -0.1700
Data Index: 6012143 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1403. Min Range: -7.1403
Max Act: 6.6716. Min Act: -0.1700
Data Index: 243940 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1403. Min Range: -7.1403
Max Act: 6.6716. Min Act: -0.1700
Data Index: 3212006 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1403. Min Range: -7.1403
Max Act: 6.6403. Min Act: -0.1700
Data Index: 1047664 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1403. Min Range: -7.1403
Max Act: 6.6091. Min Act: -0.1700
Data Index: 1072605 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1403. Min Range: -7.1403
Max Act: 6.6091. Min Act: -0.1700
Data Index: 77352 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19