Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3398 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4610. Min Range: -6.4610
Max Act: 6.4610. Min Act: -0.1700
Data Index: 6873646 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4610. Min Range: -6.4610
Max Act: 6.4610. Min Act: -0.1700
Data Index: 6789500 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4610. Min Range: -6.4610
Max Act: 6.4297. Min Act: -0.1700
Data Index: 4789706 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4610. Min Range: -6.4610
Max Act: 6.3985. Min Act: -0.1700
Data Index: 469473 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4610. Min Range: -6.4610
Max Act: 6.3360. Min Act: -0.1700
Data Index: 169171 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4610. Min Range: -6.4610
Max Act: 6.3672. Min Act: -0.1700
Data Index: 2068649 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4610. Min Range: -6.4610
Max Act: 6.3360. Min Act: -0.1700
Data Index: 6309868 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4610. Min Range: -6.4610
Max Act: 6.2735. Min Act: -0.1700
Data Index: 6613285 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4610. Min Range: -6.4610
Max Act: 6.2422. Min Act: -0.1700
Data Index: 6172396 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4610. Min Range: -6.4610
Max Act: 6.2422. Min Act: -0.1700
Data Index: 200347 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4610. Min Range: -6.4610
Max Act: 6.2422. Min Act: -0.1700
Data Index: 5299254 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4610. Min Range: -6.4610
Max Act: 6.2422. Min Act: -0.1700
Data Index: 1608739 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4610. Min Range: -6.4610
Max Act: 6.2422. Min Act: -0.1700
Data Index: 5319258 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4610. Min Range: -6.4610
Max Act: 6.2110. Min Act: -0.1700
Data Index: 881848 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4610. Min Range: -6.4610
Max Act: 6.2422. Min Act: -0.1700
Data Index: 2207346 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4610. Min Range: -6.4610
Max Act: 6.1797. Min Act: -0.1700
Data Index: 2458186 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4610. Min Range: -6.4610
Max Act: 6.2110. Min Act: -0.1700
Data Index: 1863790 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4610. Min Range: -6.4610
Max Act: 6.2110. Min Act: -0.1700
Data Index: 4829927 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4610. Min Range: -6.4610
Max Act: 6.2110. Min Act: -0.1700
Data Index: 6971164 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4610. Min Range: -6.4610
Max Act: 6.1797. Min Act: -0.1700
Data Index: 605332 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #19