Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4889 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8528. Min Range: -5.8528
Max Act: 5.8528. Min Act: -0.1700
Data Index: 8409846 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8528. Min Range: -5.8528
Max Act: 5.6965. Min Act: -0.1700
Data Index: 3013619 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8528. Min Range: -5.8528
Max Act: 5.6028. Min Act: -0.1700
Data Index: 3189465 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8528. Min Range: -5.8528
Max Act: 5.5715. Min Act: -0.1700
Data Index: 491900 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8528. Min Range: -5.8528
Max Act: 5.4778. Min Act: -0.1700
Data Index: 6328000 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8528. Min Range: -5.8528
Max Act: 5.5090. Min Act: -0.1700
Data Index: 3614953 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8528. Min Range: -5.8528
Max Act: 5.4153. Min Act: -0.1700
Data Index: 13855 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8528. Min Range: -5.8528
Max Act: 5.4778. Min Act: -0.1700
Data Index: 638838 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8528. Min Range: -5.8528
Max Act: 5.4465. Min Act: -0.1700
Data Index: 6488664 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8528. Min Range: -5.8528
Max Act: 5.4153. Min Act: -0.1700
Data Index: 3258398 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8528. Min Range: -5.8528
Max Act: 5.4153. Min Act: -0.1700
Data Index: 7889725 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8528. Min Range: -5.8528
Max Act: 5.3840. Min Act: -0.1700
Data Index: 243615 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8528. Min Range: -5.8528
Max Act: 5.4153. Min Act: -0.1700
Data Index: 6051444 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8528. Min Range: -5.8528
Max Act: 5.3840. Min Act: -0.1700
Data Index: 4300 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8528. Min Range: -5.8528
Max Act: 5.3840. Min Act: -0.1700
Data Index: 2219825 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8528. Min Range: -5.8528
Max Act: 5.3840. Min Act: -0.1700
Data Index: 6597739 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8528. Min Range: -5.8528
Max Act: 5.3840. Min Act: -0.1700
Data Index: 1305923 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8528. Min Range: -5.8528
Max Act: 5.4153. Min Act: -0.1700
Data Index: 5594224 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8528. Min Range: -5.8528
Max Act: 5.3528. Min Act: -0.1700
Data Index: 3621518 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8528. Min Range: -5.8528
Max Act: 5.3840. Min Act: -0.1700
Data Index: 102533 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19