Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2562 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.7775. Min Range: -11.7775
Max Act: 11.7775. Min Act: -0.1700
Data Index: 4820884 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.7775. Min Range: -11.7775
Max Act: 11.3400. Min Act: -0.1700
Data Index: 1312807 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.7775. Min Range: -11.7775
Max Act: 11.0275. Min Act: -0.1700
Data Index: 1368836 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.7775. Min Range: -11.7775
Max Act: 10.9025. Min Act: -0.1700
Data Index: 3422799 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.7775. Min Range: -11.7775
Max Act: 10.9025. Min Act: -0.1700
Data Index: 3997212 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.7775. Min Range: -11.7775
Max Act: 10.9025. Min Act: -0.1700
Data Index: 4558628 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.7775. Min Range: -11.7775
Max Act: 10.8400. Min Act: -0.1700
Data Index: 8112019 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.7775. Min Range: -11.7775
Max Act: 10.7775. Min Act: -0.1700
Data Index: 915983 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.7775. Min Range: -11.7775
Max Act: 10.7775. Min Act: -0.1700
Data Index: 1277409 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.7775. Min Range: -11.7775
Max Act: 10.7775. Min Act: -0.1700
Data Index: 5860167 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.7775. Min Range: -11.7775
Max Act: 10.7150. Min Act: -0.1700
Data Index: 7215559 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.7775. Min Range: -11.7775
Max Act: 10.5900. Min Act: -0.1700
Data Index: 747262 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.7775. Min Range: -11.7775
Max Act: 10.5900. Min Act: -0.1700
Data Index: 6660691 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.7775. Min Range: -11.7775
Max Act: 10.5900. Min Act: -0.1700
Data Index: 7819408 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.7775. Min Range: -11.7775
Max Act: 10.6525. Min Act: -0.1700
Data Index: 1992574 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.7775. Min Range: -11.7775
Max Act: 10.5900. Min Act: -0.1700
Data Index: 1209843 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.7775. Min Range: -11.7775
Max Act: 10.5275. Min Act: -0.1700
Data Index: 8807260 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.7775. Min Range: -11.7775
Max Act: 10.4650. Min Act: -0.1700
Data Index: 7742941 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.7775. Min Range: -11.7775
Max Act: 10.4650. Min Act: -0.1700
Data Index: 5232178 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.7775. Min Range: -11.7775
Max Act: 10.4650. Min Act: -0.1700
Data Index: 262633 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19