Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4949 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9916. Min Range: -6.9916
Max Act: 6.9916. Min Act: -0.1700
Data Index: 1742746 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9916. Min Range: -6.9916
Max Act: 6.8354. Min Act: -0.1700
Data Index: 67191 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9916. Min Range: -6.9916
Max Act: 6.7729. Min Act: -0.1700
Data Index: 1467017 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9916. Min Range: -6.9916
Max Act: 6.7729. Min Act: -0.1700
Data Index: 2598158 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9916. Min Range: -6.9916
Max Act: 6.7104. Min Act: -0.1700
Data Index: 4595156 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9916. Min Range: -6.9916
Max Act: 6.7104. Min Act: -0.1700
Data Index: 3314307 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9916. Min Range: -6.9916
Max Act: 6.6479. Min Act: -0.1700
Data Index: 8567963 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9916. Min Range: -6.9916
Max Act: 6.6479. Min Act: -0.1700
Data Index: 1137581 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9916. Min Range: -6.9916
Max Act: 6.6166. Min Act: -0.1700
Data Index: 916978 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9916. Min Range: -6.9916
Max Act: 6.6166. Min Act: -0.1700
Data Index: 1601633 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9916. Min Range: -6.9916
Max Act: 6.6166. Min Act: -0.1700
Data Index: 7144395 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9916. Min Range: -6.9916
Max Act: 6.6166. Min Act: -0.1700
Data Index: 1193114 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9916. Min Range: -6.9916
Max Act: 6.6166. Min Act: -0.1700
Data Index: 1136035 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9916. Min Range: -6.9916
Max Act: 6.5854. Min Act: -0.1700
Data Index: 567585 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9916. Min Range: -6.9916
Max Act: 6.5541. Min Act: -0.1700
Data Index: 1208586 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9916. Min Range: -6.9916
Max Act: 6.5854. Min Act: -0.1700
Data Index: 4643762 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9916. Min Range: -6.9916
Max Act: 6.5854. Min Act: -0.1700
Data Index: 8023068 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9916. Min Range: -6.9916
Max Act: 6.5854. Min Act: -0.1700
Data Index: 1021257 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9916. Min Range: -6.9916
Max Act: 6.5854. Min Act: -0.1700
Data Index: 5139504 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9916. Min Range: -6.9916
Max Act: 6.5541. Min Act: -0.1700
Data Index: 1625940 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19