Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2065 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5344. Min Range: -5.5344
Max Act: 5.5344. Min Act: -0.1666
Data Index: 88905 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5344. Min Range: -5.5344
Max Act: 5.4407. Min Act: -0.1699
Data Index: 88904 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5344. Min Range: -5.5344
Max Act: 5.2532. Min Act: -0.1694
Data Index: 3944363 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5344. Min Range: -5.5344
Max Act: 4.9094. Min Act: -0.1697
Data Index: 4084881 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5344. Min Range: -5.5344
Max Act: 4.8469. Min Act: -0.1621
Data Index: 88903 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5344. Min Range: -5.5344
Max Act: 4.8469. Min Act: -0.1700
Data Index: 583698 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5344. Min Range: -5.5344
Max Act: 4.8469. Min Act: -0.1700
Data Index: 583701 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5344. Min Range: -5.5344
Max Act: 4.8157. Min Act: -0.1700
Data Index: 5840513 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5344. Min Range: -5.5344
Max Act: 4.6594. Min Act: -0.1700
Data Index: 1610850 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5344. Min Range: -5.5344
Max Act: 4.6282. Min Act: -0.1700
Data Index: 26366 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5344. Min Range: -5.5344
Max Act: 4.5657. Min Act: -0.1697
Data Index: 6782690 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5344. Min Range: -5.5344
Max Act: 4.5500. Min Act: -0.1697
Data Index: 4514350 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5344. Min Range: -5.5344
Max Act: 4.5657. Min Act: -0.1700
Data Index: 3812224 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5344. Min Range: -5.5344
Max Act: 4.5500. Min Act: -0.1700
Data Index: 583711 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5344. Min Range: -5.5344
Max Act: 4.5344. Min Act: -0.1700
Data Index: 5840514 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5344. Min Range: -5.5344
Max Act: 4.4875. Min Act: -0.1700
Data Index: 3390870 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5344. Min Range: -5.5344
Max Act: 4.4563. Min Act: -0.1700
Data Index: 5840512 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5344. Min Range: -5.5344
Max Act: 4.3938. Min Act: -0.1700
Data Index: 2789102 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5344. Min Range: -5.5344
Max Act: 4.4094. Min Act: -0.1672
Data Index: 583710 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5344. Min Range: -5.5344
Max Act: 4.3782. Min Act: -0.1609
Data Index: 5020693 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #19