Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4591 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6840. Min Range: -6.6840
Max Act: 6.6840. Min Act: -0.1700
Data Index: 8202920 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6840. Min Range: -6.6840
Max Act: 6.6527. Min Act: -0.1700
Data Index: 7968412 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6840. Min Range: -6.6840
Max Act: 6.5902. Min Act: -0.1700
Data Index: 2493657 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6840. Min Range: -6.6840
Max Act: 6.5590. Min Act: -0.1700
Data Index: 4631846 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6840. Min Range: -6.6840
Max Act: 6.4027. Min Act: -0.1700
Data Index: 5527401 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6840. Min Range: -6.6840
Max Act: 6.3090. Min Act: -0.1700
Data Index: 4779288 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6840. Min Range: -6.6840
Max Act: 6.3090. Min Act: -0.1700
Data Index: 34207 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6840. Min Range: -6.6840
Max Act: 6.2777. Min Act: -0.1700
Data Index: 568922 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6840. Min Range: -6.6840
Max Act: 6.2465. Min Act: -0.1700
Data Index: 5730498 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6840. Min Range: -6.6840
Max Act: 6.2465. Min Act: -0.1700
Data Index: 4553573 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6840. Min Range: -6.6840
Max Act: 6.2777. Min Act: -0.1700
Data Index: 7677325 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6840. Min Range: -6.6840
Max Act: 6.1840. Min Act: -0.1700
Data Index: 3238177 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6840. Min Range: -6.6840
Max Act: 6.1527. Min Act: -0.1700
Data Index: 2765741 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6840. Min Range: -6.6840
Max Act: 6.1527. Min Act: -0.1700
Data Index: 8798744 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6840. Min Range: -6.6840
Max Act: 6.1215. Min Act: -0.1700
Data Index: 2841183 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6840. Min Range: -6.6840
Max Act: 6.1527. Min Act: -0.1700
Data Index: 4023171 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6840. Min Range: -6.6840
Max Act: 6.1215. Min Act: -0.1700
Data Index: 3518263 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6840. Min Range: -6.6840
Max Act: 6.1215. Min Act: -0.1700
Data Index: 2157556 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6840. Min Range: -6.6840
Max Act: 6.1215. Min Act: -0.1700
Data Index: 270740 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6840. Min Range: -6.6840
Max Act: 6.0902. Min Act: -0.1700
Data Index: 2084226 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19