Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4074 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3715. Min Range: -6.3715
Max Act: 6.3715. Min Act: -0.1700
Data Index: 7159824 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3715. Min Range: -6.3715
Max Act: 6.3403. Min Act: -0.1700
Data Index: 8581466 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3715. Min Range: -6.3715
Max Act: 6.2778. Min Act: -0.1700
Data Index: 8390516 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3715. Min Range: -6.3715
Max Act: 6.1215. Min Act: -0.1700
Data Index: 7934777 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3715. Min Range: -6.3715
Max Act: 6.0903. Min Act: -0.1700
Data Index: 5923046 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3715. Min Range: -6.3715
Max Act: 5.9653. Min Act: -0.1700
Data Index: 6385432 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3715. Min Range: -6.3715
Max Act: 5.9653. Min Act: -0.1700
Data Index: 5907235 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3715. Min Range: -6.3715
Max Act: 5.9340. Min Act: -0.1700
Data Index: 3544219 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3715. Min Range: -6.3715
Max Act: 5.8715. Min Act: -0.1700
Data Index: 5292637 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3715. Min Range: -6.3715
Max Act: 5.9028. Min Act: -0.1700
Data Index: 3848142 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3715. Min Range: -6.3715
Max Act: 5.8403. Min Act: -0.1700
Data Index: 6292891 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3715. Min Range: -6.3715
Max Act: 5.8403. Min Act: -0.1700
Data Index: 1314270 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3715. Min Range: -6.3715
Max Act: 5.7465. Min Act: -0.1700
Data Index: 4442336 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3715. Min Range: -6.3715
Max Act: 5.7778. Min Act: -0.1700
Data Index: 6656935 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3715. Min Range: -6.3715
Max Act: 5.7153. Min Act: -0.1700
Data Index: 42621 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3715. Min Range: -6.3715
Max Act: 5.6840. Min Act: -0.1700
Data Index: 2013937 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3715. Min Range: -6.3715
Max Act: 5.6840. Min Act: -0.1700
Data Index: 5865293 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3715. Min Range: -6.3715
Max Act: 5.6840. Min Act: -0.1700
Data Index: 2052716 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3715. Min Range: -6.3715
Max Act: 5.6528. Min Act: -0.1700
Data Index: 256 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3715. Min Range: -6.3715
Max Act: 5.6840. Min Act: -0.1700
Data Index: 743915 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19